@proceedings{gem-2026-main,
    title = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.0/",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{huber-etal-2026-cosy,
    title = "{C}o{S}y: Conversational Synthesis for Grounded Question Answering",
    author = "Huber, Patrick  and
      Einolghozati, Arash  and
      Conway, Rylan  and
      Narang, Kanika  and
      Smith, Matt  and
      Nayyar, Waqar  and
      Sagar, Adithya  and
      Aly, Ahmed A  and
      Shrivastava, Akshat",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.2/",
    pages = "1--10",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{shah-etal-2026-vaidya,
    title = "{VAIDYA}: Validated Agents for Intelligent Diagnosis and Yielded Analysis",
    author = "Shah, Kalash  and
      Bhutani, Gautam  and
      Sarbhangia, Rohitaswa  and
      Snehan, J",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.3/",
    pages = "11--33",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{harshavardhan-2026-self,
    title = "Self-Anchoring Calibration Drift in Large Language Models: How Multi-Turn Conversations Reshape Model Confidence",
    author = "Harshavardhan",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.4/",
    pages = "34--40",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{liu-etal-2026-temporal-tokenization,
    title = "Temporal Tokenization Strategies for Event Sequence Modeling with Large Language Models",
    author = "Liu, Zefang  and
      Nguyen, Nam H  and
      Quan, Yinzhu  and
      Zhang, Shi-Xiong",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.5/",
    pages = "41--51",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{van-doren-etal-2026-cheese,
    title = "``Be My Cheese?'': Cultural Nuance Benchmarking for Machine Translation in Multilingual {LLM}s",
    author = "Van Doren, Madison  and
      Ford, Casey  and
      Barajas, Jennifer  and
      VanMeter, Riley  and
      Holland, Cory",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.6/",
    pages = "52--76",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{tiwari-2026-component,
    title = "Component Transfer Can Exceed Full Model Performance: Investigating Post-Trained Mixture-of-Experts",
    author = "Tiwari, Rabin",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.7/",
    pages = "77--83",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{ho-etal-2026-reassessing,
    title = "Reassessing Extractive {QA} Datasets at Scale: {LLM}-as-a-Judge and In-Depth Analyses",
    author = "Ho, Xanh  and
      Huang, Jiahao  and
      Boudin, Florian  and
      Aizawa, Akiko",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.9/",
    pages = "84--101",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{jajee-etal-2026-indicmmlu,
    title = "{I}ndic{MMLU}-Pro: Benchmarking {I}ndic Large Language Models on Multi-Task Language Understanding",
    author = "Jajee, Sankalp  and
      Kumar, Ashutosh  and
      Kotecha, Nikunj  and
      Jain, Vinija  and
      Chadha, Aman  and
      Bhaduri, Sreyoshi",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.10/",
    pages = "102--111",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{ho-etal-2026-identifying,
    title = "Identifying Where Large Language Models Struggle in Answering Complex Questions",
    author = "Ho, Xanh  and
      Boudin, Florian  and
      Sugawara, Saku  and
      Duong, Khoa  and
      Aizawa, Akiko",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.11/",
    pages = "112--123",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{igitkhanian-arakelyan-2026-yap,
    title = "More Yap Less Meaning: Uncovering Self-Improvement Behavior in {SLM}s",
    author = "Igitkhanian, Marina  and
      Arakelyan, Erik",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.12/",
    pages = "124--135",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{ta-etal-2026-reinforced,
    title = "Reinforced Agent: Inference-Time Feedback for Tool-Calling Agents",
    author = "Ta, Anh  and
      Zhu, Junjie  and
      Shayandeh, Shahin",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.13/",
    pages = "136--147",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{malreddy-etal-2026-ad,
    title = "{RE}-{AD}: Real-Time Requirement Adherence for Data Labeling",
    author = "Malreddy, Siddarth  and
      Nigam, Ishan  and
      Arora, Akshay  and
      Mittal, Nikhil  and
      Sahu, Subrat",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.17/",
    pages = "148--154",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{hamilton-mimno-2026-lost,
    title = "Lost in Space: Finding the Right Tokens for Structured Output",
    author = "Hamilton, Sil  and
      Mimno, David",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.18/",
    pages = "155--166",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{yamauchi-etal-2026-empirical,
    title = "An Empirical Study of {LLM}-as-a-Judge: How Design Choices Impact Evaluation Reliability",
    author = "Yamauchi, Yusuke  and
      Yano, Taro  and
      Oyamada, Masafumi",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.19/",
    pages = "167--176",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{jiang-liang-2026-capturing,
    title = "Capturing Epistemic Uncertainty in {LLM}-Based Soft Labeling",
    author = "Jiang, Yanru  and
      Liang, Siyu",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.21/",
    pages = "177--190",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{peter-etal-2026-mind,
    title = "Mind the Gap... or Not? How Translation Errors and Evaluation Details Skew Multilingual Results",
    author = "Peter, Jan-Thorsten  and
      Vilar, David  and
      Domhan, Tobias  and
      Malkin, Dan  and
      Freitag, Markus",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.22/",
    pages = "191--204",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{lee-etal-2026-mcjudgebench,
    title = "{MCJ}udge{B}ench: A Benchmark for Constraint-Level Judge Evaluation in Multi-Constraint Instruction Following",
    author = "Lee, Jaeyun  and
      Koh, Junyoung  and
      Tok, Zeynel  and
      Batra, Hunar  and
      Clark, Ronald",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.23/",
    pages = "205--221",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{krishna-etal-2026-medact,
    title = "{M}ed{A}ct: Removing the Human Bottleneck in Benchmarking Clinical {LLM} Safety",
    author = "Krishna, Arjun  and
      Pridgen, Brian  and
      Silverstein, Max",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.24/",
    pages = "222--230",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{park-etal-2026-response,
    title = "Response Content Units: Evaluating Completeness and Proactiveness in Medical Open-Response Question Answering",
    author = "Park, Yongsin  and
      Yim, Wen-wai  and
      McKibbin, Emma  and
      Ben Abacha, Asma  and
      Xia, Fei",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.25/",
    pages = "231--252",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{anantha-etal-2026-nanoflux,
    title = "{N}ano{F}lux: Adversarial Dual-{LLM} Evaluation and Distillation for Multi-Domain Reasoning",
    author = "Anantha, Raviteja  and
      Hor, Soheil  and
      Antoniu, Teodor Nicola  and
      Price, Layne C",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.27/",
    pages = "253--270",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{datta-etal-2026-evaluating,
    title = "Evaluating the Reliability of {LLM}s in Faithfully Updating Text: An Empirical Study",
    author = "Datta, Ayan  and
      Bhattacharya, Paheli  and
      Gupta, Rishabh",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.28/",
    pages = "271--284",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{dash-etal-2026-tokens,
    title = "Not All Tokens Are Equal: Per-Dimension Top-K Pooling for Adversarially Robust {BERT} Classification",
    author = "Dash, Manoranjan  and
      Aralikatti, Shivam Anand  and
      Sheth, Shanay  and
      Shinde, Pranav",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.29/",
    pages = "285--295",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{rabinovich-etal-2026-near,
    title = "Near-Miss: Latent Policy Failure Detection in Agentic Workflows",
    author = "Rabinovich, Ella  and
      Boaz, David  and
      Zwerdling, Naama  and
      Anaby Tavor, Ateret",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.30/",
    pages = "296--308",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{georgousis-etal-2026-evaluating,
    title = "Evaluating Counterfactual Strategic Reasoning in Large Language Models",
    author = "Georgousis, Dimitrios  and
      Lymperaiou, Maria  and
      Dimitriou, Angeliki  and
      Filandrianos, Giorgos  and
      Stamou, Giorgos",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.31/",
    pages = "309--354",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{gupta-etal-2026-speculative,
    title = "Speculative Refinement: A Hybrid Autoregressive Diffusion Decoding Strategy and Its Behavior Across Benchmarks",
    author = "Gupta, Aditi  and
      Mishra, Neel  and
      Trivedi, Kushagra  and
      Kumar, Pawan",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.33/",
    pages = "355--363",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{sung-etal-2026-sauce,
    title = "{SAUCE}: Summary Analysis Using Conversation Entailment",
    author = "Sung, Man-Ling  and
      Kandula, Hemanth  and
      Ma, Jeff  and
      Hartmann, William  and
      Snover, Matthew",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.34/",
    pages = "364--377",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{hande-etal-2026-evaluating,
    title = "Evaluating {ASR} Quality at Scale on {TV} Entertainment Platforms",
    author = "Hande, Adeep  and
      Sundararajan, Kishorekumar  and
      Endale, Yidnekachew  and
      Bapu KrishnaSwamy, Akshatha  and
      Dabral, Sachin  and
      Reed, Dawn  and
      Pereira, Michael",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.35/",
    pages = "378--383",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{yang-etal-2026-fine,
    title = "Fine-Tuning vs. {RAG} for Multi-Hop Question Answering with Novel Knowledge",
    author = "Yang, Zhuoyi  and
      Song, Yurun  and
      Harris, Kyler G.  and
      Ahmed, Iftekhar  and
      Harris, Ian",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.37/",
    pages = "384--392",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{liu-etal-2026-mhgraphbench,
    title = "{MHG}raph{B}ench: Knowledge Graph-Grounded Benchmarking of Mental Health Knowledge in Large Language Models",
    author = "Liu, Weixin  and
      Ni, Congning  and
      Mulvaney, Shelagh A.  and
      Rose, Susannah L.  and
      Kantarcioglu, Murat  and
      Malin, Bradley A.  and
      Yin, Zhijun",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.38/",
    pages = "393--409",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{kapuriya-etal-2026-progressive,
    title = "A Progressive Evaluation Framework for Multicultural Analysis of Story Visualization",
    author = "Kapuriya, Janak  and
      Hatami, Ali  and
      Buitelaar, Paul",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.39/",
    pages = "410--427",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{chen-etal-2026-graphrag,
    title = "Is {G}raph{RAG} Needed? From Basic {RAG} to Graph-/Agentic Solutions with Context Optimization",
    author = "Chen, Long  and
      Razkenari, Ryan  and
      Zhou, Yuxuan  and
      Tian, Yuan  and
      Ghosh, Rahul  and
      Pappakrishnan, Venkatesh  and
      Ahuja, Disha  and
      Ravipati, Vidya Sagar",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.40/",
    pages = "428--442",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{harrison-walker-2026-cross,
    title = "Cross-Domain Semantic Fidelity Evaluation for Meaning-to-Text Generation",
    author = "Harrison, Davan  and
      Walker, Marilyn",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.41/",
    pages = "443--455",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{kwon-etal-2026-e,
    title = "{E}-star 12{B}: Reliable Rubric-Following and Domain-Adaptive {SLM} Evaluator for {K}orean Industrial Settings",
    author = "Kwon, Yonghoon  and
      Lee, Heondeuk  and
      Kang, Barom",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.42/",
    pages = "456--471",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{kumar-2026-pressure,
    title = "Pressure-Testing Deception Probes in {LLM}s: Scaling, Robustness, and the Geometry of Deceptive Representations",
    author = "Kumar, Sachin",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.43/",
    pages = "472--489",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{farzi-etal-2026-sycophancy,
    title = "Sycophancy Negatively Affects {LLM}-as-a-Judge in Conflict Evaluation",
    author = "Farzi, Naghmeh  and
      Dietz, Laura  and
      Carton, Samuel",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.45/",
    pages = "490--501",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{bliss-etal-2026-concord,
    title = "Concord: An Agreement-Aware Multi-Adjudication Pipeline for {LLM} Evaluation",
    author = "Bliss, Tyler  and
      Verma, Mahit  and
      Iyer-Singh, Aila  and
      Biswas, Subrata  and
      Imran, Sheikh Asif  and
      Islam, Bashima",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.46/",
    pages = "502--510",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{badhe-etal-2026-silent,
    title = "The Silent Vote: Improving Zero-Shot {LLM} Reliability by Aggregating Semantic Neighborhoods",
    author = "Badhe, Sanket  and
      Tiwari, Priyanka  and
      Shah, Deep",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.48/",
    pages = "511--517",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{nourbakhsh-etal-2026-llm,
    title = "Are {LLM} Benchmarks Already Contaminated? A Systematic Review of Contamination Detection Methods",
    author = "Nourbakhsh, Erfan  and
      Sirjani, Mohammad Sadegh  and
      Mousavi, Amir  and
      Nguyen, Khoa  and
      Quarles, John  and
      Xie, Mimi  and
      Slavin, Rocky",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.50/",
    pages = "518--539",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{bhatt-ivanova-2026-rbcorr,
    title = "{RBC}orr: Response Bias Correction in Language Models",
    author = "Bhatt, Om  and
      Ivanova, Anna A",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.51/",
    pages = "540--553",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{campese-lauriola-2026-exploring,
    title = "Exploring Coherence of {LLM}s in Multilingual Question Answering",
    author = "Campese, Stefano  and
      Lauriola, Ivano",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.52/",
    pages = "554--562",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{jamil-etal-2026-token,
    title = "Token Cost Inequality: Measuring Tokenization Disparities Across Scripts in {R}oman {U}rdu and {U}rdu",
    author = "Jamil, Waleed  and
      Rafi, Saima  and
      Yu, Yanchao",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.54/",
    pages = "563--573",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{fedrushkov-etal-2026-semantic,
    title = "Semantic vs. Structural Signals: Log-Probability and {LLM}-as-a-Judge for Reference-Free Code Evaluation",
    author = "Fedrushkov, Dmitriy  and
      He, Yulong  and
      Smirnov, Ivan  and
      Aliev, Artem  and
      Kovalchuk, Sergey",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.55/",
    pages = "574--581",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{dutta-moharir-2026-stability,
    title = "Stability vs. Manipulability: Evaluating Robustness Under Post-Decision Interaction in {LLM} Judges",
    author = "Dutta, Srimonti  and
      Moharir, Akshata Kishore",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.57/",
    pages = "582--594",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{huang-etal-2026-permutation,
    title = "Permutation-Consensus Listwise Judging for Robust Factuality Evaluation",
    author = "Huang, Tianyi  and
      Huang, Nathan  and
      Tang, Justin  and
      Chen, Wenqian  and
      Fan, Elsa",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.58/",
    pages = "595--603",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{he-etal-2026-medfact,
    title = "{M}ed{F}act: Benchmarking the Fact-Checking Capabilities of Large Language Models on {C}hinese Medical Texts",
    author = "He, Jiayi  and
      Huang, Yangmin  and
      Du, Qianyun  and
      Zhou, Xiangying  and
      He, Zhiyang  and
      Hu, Jiaxue  and
      Tao, Xiaodong  and
      Lai, Lixian",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.59/",
    pages = "604--652",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{keramati-etal-2026-early,
    title = "Early-Token Confidence Predicts Reasoning Quality in Multi-Agent {LLM} Debate",
    author = "Keramati, Ali  and
      Cheok, Justin  and
      Horne, Jacob  and
      Warschauer, Mark",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.60/",
    pages = "653--667",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{mehta-etal-2026-complex,
    title = "Complex-{IF} and Beyond: Expert Rubrics for {RLVR}",
    author = "Mehta, Sushant  and
      Panavas, Liudas  and
      Fleming, Eleanor  and
      Mains, Paul  and
      Chen, Edwin",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.61/",
    pages = "668--677",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{mittal-arike-2026-c2,
    title = "C2-Faith: Benchmarking {LLM} Judges for Causal and Coverage Faithfulness in Chain-of-Thought Reasoning",
    author = "Mittal, Avni  and
      Arike, Rauno",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.62/",
    pages = "678--691",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{strozyna-etal-2026-evaluating,
    title = "Evaluating Multilingual Sentiment Classifiers Using an {LLM}-Annotated {W}ikipedia Benchmark",
    author = "Str{\'o}{\.z}yna, Milena  and
      Lewoniewski, W{\l}odzimierz  and
      Czuma{\l}owska, Izabela",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.63/",
    pages = "692--703",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{thomson-etal-2026-process,
    title = "Process Standardisation for Human Evaluation of {NLP} System Outputs",
    author = "Thomson, Craig  and
      Gonz{\'a}lez Corbelle, Javier  and
      Belz, Anya",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.64/",
    pages = "704--717",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{tatarinov-etal-2026-language,
    title = "Language Modeling for the Future of Finance: A Survey into Metrics, Tasks, and Data Opportunities",
    author = "Tatarinov, Nikita  and
      Sukhani, Siddhant  and
      Shah, Agam  and
      Chava, Sudheer",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.65/",
    pages = "718--744",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{lior-etal-2026-wildifeval,
    title = "{W}ild{IFE}val: Instruction Following in the Wild",
    author = "Lior, Gili  and
      Yehudai, Asaf  and
      Gera, Ariel  and
      Ein-Dor, Liat",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.66/",
    pages = "745--778",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{liu-quan-2026-econwebarena,
    title = "{E}con{W}eb{A}rena: Benchmarking Autonomous Agents on Economic Tasks in Realistic Web Environments",
    author = "Liu, Zefang  and
      Quan, Yinzhu",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.67/",
    pages = "779--796",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{sadana-etal-2026-iso,
    title = "{ISO}-Bench: Benchmarking Multimodal Causal Reasoning in Visual{--}Language Models through Procedural Plans",
    author = "Sadana, Ananya  and
      Lal, Yash Kumar  and
      Zhou, Jiawei",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.68/",
    pages = "797--807",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{shi-etal-2026-text,
    title = "Text Analytics Evaluation Framework: A Case Study on {LLM}s and Social Media",
    author = "Shi, Yuefeng  and
      Ousidhoum, Nedjma  and
      Camacho-Collados, Jose",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.69/",
    pages = "808--824",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{yehudai-etal-2026-teaching,
    title = "Teaching Values to Machines: Simulating Human-Like Behavior in {LLM}s",
    author = "Yehudai, Asaf  and
      Rozen, Naama  and
      Gera, Ariel",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.70/",
    pages = "825--847",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{pedinotti-etal-2026-metagraph,
    title = "{M}eta{G}raph: A Large-Scale Meta-Analysis of {G}en{AI} in Financial {NLP} (2022{--}2025)",
    author = "Pedinotti, Paolo  and
      Baumann, Peter  and
      Jessurun, Nathan  and
      Barrett, Leslie  and
      Santus, Enrico",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.71/",
    pages = "848--861",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{shourya-etal-2026-users,
    title = "When Users Are Happy but Agents Are Wrong: Multi-Dimensional Evaluation of Tool-Augmented Dialogue",
    author = "Shourya, Tanya  and
      Wang, Yingfan  and
      Hou, Zhaoyi Joey  and
      Roy, Shamik  and
      Kumar, Vinayshekhar Bannihatti  and
      Gangadharaiah, Rashmi",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.72/",
    pages = "862--892",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{nathan-etal-2026-tool,
    title = "Tool-Aware Planning for Contact-Center Analytics: Evaluating {LLM}s through Lineage-Guided Query Decomposition",
    author = "Nathan, Varun  and
      Guha, Shreyas  and
      Kumar, Ayush",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.73/",
    pages = "893--943",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{jing-etal-2026-tsaqa,
    title = "{TSAQA}: Time Series Analysis Question And Answering Benchmark",
    author = "Jing, Baoyu  and
      Chen, Sanhorn  and
      Zheng, Lecheng  and
      Liu, Boyu  and
      Li, Zihao  and
      Zou, Jiaru  and
      Wei, Tianxin  and
      Liu, Zhining  and
      Zeng, Zhichen  and
      Qiu, Ruizhong  and
      Lin, Xiao  and
      Yan, Yuchen  and
      Fu, Dongqi  and
      Ni, Jingchao  and
      He, Jingrui  and
      Tong, Hanghang",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.74/",
    pages = "944--979",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{mammen-etal-2026-endorsed,
    title = "Who Endorsed It? Measuring Authority Bias Across Expertise Levels in Language Models",
    author = "Mammen, Priyanka Mary  and
      Joswin, Emil  and
      Venkitachalam, Shankar",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.75/",
    pages = "980--989",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{ali-etal-2026-reference,
    title = "Reference Games as a Testbed for the Alignment of Model Uncertainty and Clarification Requests",
    author = "Ali, Manar  and
      Sieker, Judith  and
      Zarrie{\ss}, Sina  and
      Buschmeier, Hendrik",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.76/",
    pages = "990--998",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{belz-etal-2026-mapping,
    title = "Mapping Out the {NLP} Evaluation Landscape with a Standard Taxonomy of Quality Criteria",
    author = "Belz, Anya  and
      Mille, Simon  and
      Thomson, Craig",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.77/",
    pages = "999--1014",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{catapang-2026-position,
    title = "Position: Toward a Metric Typology for Language Model Evaluation",
    author = "Catapang, Jasper Kyle",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.78/",
    pages = "1015--1020",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{zaghouani-2026-position,
    title = "Position: What Are We Measuring? Rethinking Evaluation in Natural Language Generation",
    author = "Zaghouani, Wajdi",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.79/",
    pages = "1021--1028",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{gilda-gilda-2026-position,
    title = "Position: Evaluation Scores Are Perishable Knowledge Claims",
    author = "Gilda, Sankalp  and
      Gilda, Shlok",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.80/",
    pages = "1029--1035",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{perez-etal-2026-position,
    title = "Position: A Semiotic-Hermeneutic Approach to Evaluating Meaning in {LLM} Summaries via the Inductive Conceptual Rating Metric",
    author = "Perez, Natalie  and
      Bhaduri, Sreyoshi  and
      Chadha, Aman",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.81/",
    pages = "1036--1047",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{zhou-2026-position,
    title = "Position: Scores Without Context? Rethinking the Role of Evaluation in the Era of {LLM}s",
    author = "Zhou, Jiawei",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.82/",
    pages = "1048--1054",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{belz-etal-2026-shared,
    title = "The Shared Task on Reproducibility of Evaluations in {NLP} ({R}epro{NLP}) 2026: Overview and Results",
    author = "Belz, Anya  and
      Thomson, Craig  and
      Gonz{\'a}lez Corbelle, Javier",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.83/",
    pages = "1055--1070",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{ardestani-etal-2026-nugget,
    title = "Do Nugget-Based Evaluation Patterns Generalize to List-{QA}?",
    author = "Ardestani, MohammadJavad  and
      Kamalloo, Ehsan  and
      Rafiei, Davood",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.84/",
    pages = "1071--1081",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{mroczek-etal-2026-repronlp,
    title = "{R}epro{NLP} 2026: A Third Replication of the Human Evaluation of a {QAG} System for Children{'}s Storybooks",
    author = "Mroczek, Marcel  and
      Albarello, Chiara  and
      Floch, Paul-Emmanuel  and
      Gawinecki, Maciej",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.85/",
    pages = "1082--1093",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{langner-2026-reprohum,
    title = "{R}epro{H}um {\#}0124-03: Reproducing Human Scores on Neural {REG} Models",
    author = "Langner, Maurice",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.86/",
    pages = "1094--1103",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{fan-chen-2026-reprohum,
    title = "{R}epro{H}um {\#}0866-04: Variability in Human Judgments of Sociopolitical Acceptability Across Studies",
    author = "Fan, Rui  and
      Chen, Guanyi",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.87/",
    pages = "1104--1110",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{hurlimann-cieliebak-2026-reprohum,
    title = "{R}epro{H}um {\#}0031{--}01: Reproducing a Human Readability Evaluation for Question{--}Answer Generation Systems",
    author = {H{\"u}rlimann, Manuela  and
      Cieliebak, Mark},
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.88/",
    pages = "1111--1116",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{arous-cheung-2026-reprohum,
    title = "{R}epro{H}um {\#}0033-05: Human Evaluation Report on ``Generating Scientific Definitions with Controllable Complexity''",
    author = "Arous, Ines  and
      Cheung, Jackie Chi Kit",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.89/",
    pages = "1117--1126",
    ISBN = "979-8-89176-423-1"
}
@inproceedings{mahamood-2026-reprohum,
    title = "{R}epro{H}um {\#}0669-08: Reproducing a Recipe for Arbitrary Text Style Transfer with {LLM}s",
    author = "Mahamood, Saad",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.90/",
    pages = "1127--1132",
    ISBN = "979-8-89176-423-1"
}