@proceedings{eval4nlp-2023-evaluation,
    title = "Proceedings of the 4th Workshop on Evaluation and Comparison of NLP Systems",
    editor = {Deutsch, Daniel  and
      Dror, Rotem  and
      Eger, Steffen  and
      Gao, Yang  and
      Leiter, Christoph  and
      Opitz, Juri  and
      R{\"u}ckl{\'e}, Andreas},
    month = nov,
    year = "2023",
    address = "Bali, Indonesia",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-old-resolve/2023.eval4nlp-1.0/"
}
@inproceedings{weber-etal-2023-wrf,
    title = "{WRF}: Weighted Rouge-F1 Metric for Entity Recognition",
    author = "Weber, Lukas  and
      Jothi Ramalingam, Krishnan  and
      Beyer, Matthias  and
      Zimmermann, Axel",
    editor = {Deutsch, Daniel  and
      Dror, Rotem  and
      Eger, Steffen  and
      Gao, Yang  and
      Leiter, Christoph  and
      Opitz, Juri  and
      R{\"u}ckl{\'e}, Andreas},
    booktitle = "Proceedings of the 4th Workshop on Evaluation and Comparison of NLP Systems",
    month = nov,
    year = "2023",
    address = "Bali, Indonesia",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-old-resolve/2023.eval4nlp-1.1/",
    doi = "10.18653/v1/2023.eval4nlp-1.1",
    pages = "1--11"
}
@inproceedings{raina-etal-2023-assessing,
    title = "Assessing Distractors in Multiple-Choice Tests",
    author = "Raina, Vatsal  and
      Liusie, Adian  and
      Gales, Mark",
    editor = {Deutsch, Daniel  and
      Dror, Rotem  and
      Eger, Steffen  and
      Gao, Yang  and
      Leiter, Christoph  and
      Opitz, Juri  and
      R{\"u}ckl{\'e}, Andreas},
    booktitle = "Proceedings of the 4th Workshop on Evaluation and Comparison of NLP Systems",
    month = nov,
    year = "2023",
    address = "Bali, Indonesia",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-old-resolve/2023.eval4nlp-1.2/",
    doi = "10.18653/v1/2023.eval4nlp-1.2",
    pages = "12--22"
}
@inproceedings{wang-etal-2023-delving,
    title = "Delving into Evaluation Metrics for Generation: A Thorough Assessment of How Metrics Generalize to Rephrasing Across Languages",
    author = "Wang, Yixuan  and
      Chen, Qingyan  and
      Ataman, Duygu",
    editor = {Deutsch, Daniel  and
      Dror, Rotem  and
      Eger, Steffen  and
      Gao, Yang  and
      Leiter, Christoph  and
      Opitz, Juri  and
      R{\"u}ckl{\'e}, Andreas},
    booktitle = "Proceedings of the 4th Workshop on Evaluation and Comparison of NLP Systems",
    month = nov,
    year = "2023",
    address = "Bali, Indonesia",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-old-resolve/2023.eval4nlp-1.3/",
    doi = "10.18653/v1/2023.eval4nlp-1.3",
    pages = "23--31"
}
@inproceedings{kolagar-etal-2023-eduquick,
    title = "{E}du{Q}uick: A Dataset Toward Evaluating Summarization of Informal Educational Content for Social Media",
    author = "Kolagar, Zahra  and
      Steindl, Sebastian  and
      Zarcone, Alessandra",
    editor = {Deutsch, Daniel  and
      Dror, Rotem  and
      Eger, Steffen  and
      Gao, Yang  and
      Leiter, Christoph  and
      Opitz, Juri  and
      R{\"u}ckl{\'e}, Andreas},
    booktitle = "Proceedings of the 4th Workshop on Evaluation and Comparison of NLP Systems",
    month = nov,
    year = "2023",
    address = "Bali, Indonesia",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-old-resolve/2023.eval4nlp-1.4/",
    doi = "10.18653/v1/2023.eval4nlp-1.4",
    pages = "32--48"
}
@inproceedings{ramrakhiyani-etal-2023-zero,
    title = "Zero-shot Probing of Pretrained Language Models for Geography Knowledge",
    author = "Ramrakhiyani, Nitin  and
      Varma, Vasudeva  and
      Palshikar, Girish  and
      Pawar, Sachin",
    editor = {Deutsch, Daniel  and
      Dror, Rotem  and
      Eger, Steffen  and
      Gao, Yang  and
      Leiter, Christoph  and
      Opitz, Juri  and
      R{\"u}ckl{\'e}, Andreas},
    booktitle = "Proceedings of the 4th Workshop on Evaluation and Comparison of NLP Systems",
    month = nov,
    year = "2023",
    address = "Bali, Indonesia",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-old-resolve/2023.eval4nlp-1.5/",
    doi = "10.18653/v1/2023.eval4nlp-1.5",
    pages = "49--61"
}
@inproceedings{chen-eger-2023-transformers,
    title = "Transformers Go for the {LOL}s: Generating (Humourous) Titles from Scientific Abstracts End-to-End",
    author = "Chen, Yanran  and
      Eger, Steffen",
    editor = {Deutsch, Daniel  and
      Dror, Rotem  and
      Eger, Steffen  and
      Gao, Yang  and
      Leiter, Christoph  and
      Opitz, Juri  and
      R{\"u}ckl{\'e}, Andreas},
    booktitle = "Proceedings of the 4th Workshop on Evaluation and Comparison of NLP Systems",
    month = nov,
    year = "2023",
    address = "Bali, Indonesia",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-old-resolve/2023.eval4nlp-1.6/",
    doi = "10.18653/v1/2023.eval4nlp-1.6",
    pages = "62--84"
}
@inproceedings{block-etal-2023-summary,
    title = "Summary Cycles: Exploring the Impact of Prompt Engineering on Large Language Models' Interaction with Interaction Log Information",
    author = "Block, Jeremy  and
      Chen, Yu-Peng  and
      Budharapu, Abhilash  and
      Anthony, Lisa  and
      Dorr, Bonnie",
    editor = {Deutsch, Daniel  and
      Dror, Rotem  and
      Eger, Steffen  and
      Gao, Yang  and
      Leiter, Christoph  and
      Opitz, Juri  and
      R{\"u}ckl{\'e}, Andreas},
    booktitle = "Proceedings of the 4th Workshop on Evaluation and Comparison of NLP Systems",
    month = nov,
    year = "2023",
    address = "Bali, Indonesia",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-old-resolve/2023.eval4nlp-1.7/",
    doi = "10.18653/v1/2023.eval4nlp-1.7",
    pages = "85--99"
}
@inproceedings{bhat-varma-2023-large,
    title = "Large Language Models As Annotators: A Preliminary Evaluation For Annotating Low-Resource Language Content",
    author = "Bhat, Savita  and
      Varma, Vasudeva",
    editor = {Deutsch, Daniel  and
      Dror, Rotem  and
      Eger, Steffen  and
      Gao, Yang  and
      Leiter, Christoph  and
      Opitz, Juri  and
      R{\"u}ckl{\'e}, Andreas},
    booktitle = "Proceedings of the 4th Workshop on Evaluation and Comparison of NLP Systems",
    month = nov,
    year = "2023",
    address = "Bali, Indonesia",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-old-resolve/2023.eval4nlp-1.8/",
    doi = "10.18653/v1/2023.eval4nlp-1.8",
    pages = "100--107"
}
@inproceedings{doughman-etal-2023-predictions,
    title = "Can a Prediction{'}s Rank Offer a More Accurate Quantification of Bias? A Case Study Measuring Sexism in Debiased Language Models",
    author = "Doughman, Jad  and
      Shehata, Shady  and
      Al Qadi, Leen  and
      Nafea, Youssef  and
      Karray, Fakhri",
    editor = {Deutsch, Daniel  and
      Dror, Rotem  and
      Eger, Steffen  and
      Gao, Yang  and
      Leiter, Christoph  and
      Opitz, Juri  and
      R{\"u}ckl{\'e}, Andreas},
    booktitle = "Proceedings of the 4th Workshop on Evaluation and Comparison of NLP Systems",
    month = nov,
    year = "2023",
    address = "Bali, Indonesia",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-old-resolve/2023.eval4nlp-1.9/",
    doi = "10.18653/v1/2023.eval4nlp-1.9",
    pages = "108--116"
}
@inproceedings{leiter-etal-2023-eval4nlp,
    title = "The {E}val4{NLP} 2023 Shared Task on Prompting Large Language Models as Explainable Metrics",
    author = "Leiter, Christoph  and
      Opitz, Juri  and
      Deutsch, Daniel  and
      Gao, Yang  and
      Dror, Rotem  and
      Eger, Steffen",
    editor = {Deutsch, Daniel  and
      Dror, Rotem  and
      Eger, Steffen  and
      Gao, Yang  and
      Leiter, Christoph  and
      Opitz, Juri  and
      R{\"u}ckl{\'e}, Andreas},
    booktitle = "Proceedings of the 4th Workshop on Evaluation and Comparison of NLP Systems",
    month = nov,
    year = "2023",
    address = "Bali, Indonesia",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-old-resolve/2023.eval4nlp-1.10/",
    doi = "10.18653/v1/2023.eval4nlp-1.10",
    pages = "117--138"
}
@inproceedings{zhang-etal-2023-hit,
    title = "{HIT}-{MI}{\&}{T} Lab{'}s Submission to {E}val4{NLP} 2023 Shared Task",
    author = "Zhang, Rui  and
      Song, Fuhai  and
      Huang, Hui  and
      Yuan, Jinghao  and
      Yang, Muyun  and
      Zhao, Tiejun",
    editor = {Deutsch, Daniel  and
      Dror, Rotem  and
      Eger, Steffen  and
      Gao, Yang  and
      Leiter, Christoph  and
      Opitz, Juri  and
      R{\"u}ckl{\'e}, Andreas},
    booktitle = "Proceedings of the 4th Workshop on Evaluation and Comparison of NLP Systems",
    month = nov,
    year = "2023",
    address = "Bali, Indonesia",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-old-resolve/2023.eval4nlp-1.11/",
    doi = "10.18653/v1/2023.eval4nlp-1.11",
    pages = "139--148"
}
@inproceedings{pradhan-todi-2023-understanding,
    title = "Understanding Large Language Model Based Metrics for Text Summarization",
    author = "Pradhan, Abhishek  and
      Todi, Ketan",
    editor = {Deutsch, Daniel  and
      Dror, Rotem  and
      Eger, Steffen  and
      Gao, Yang  and
      Leiter, Christoph  and
      Opitz, Juri  and
      R{\"u}ckl{\'e}, Andreas},
    booktitle = "Proceedings of the 4th Workshop on Evaluation and Comparison of NLP Systems",
    month = nov,
    year = "2023",
    address = "Bali, Indonesia",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-old-resolve/2023.eval4nlp-1.12/",
    doi = "10.18653/v1/2023.eval4nlp-1.12",
    pages = "149--155"
}
@inproceedings{baswani-etal-2023-ltrc-iiiths,
    title = "{LTRC}{\_}{IIITH}{'}s 2023 Submission for Prompting Large Language Models as Explainable Metrics Task",
    author = "Baswani, Pavan  and
      Mukherjee, Ananya  and
      Shrivastava, Manish",
    editor = {Deutsch, Daniel  and
      Dror, Rotem  and
      Eger, Steffen  and
      Gao, Yang  and
      Leiter, Christoph  and
      Opitz, Juri  and
      R{\"u}ckl{\'e}, Andreas},
    booktitle = "Proceedings of the 4th Workshop on Evaluation and Comparison of NLP Systems",
    month = nov,
    year = "2023",
    address = "Bali, Indonesia",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-old-resolve/2023.eval4nlp-1.13/",
    doi = "10.18653/v1/2023.eval4nlp-1.13",
    pages = "156--163"
}
@inproceedings{kim-etal-2023-better,
    title = "Which is better? Exploring Prompting Strategy For {LLM}-based Metrics",
    author = "Kim, JoongHoon  and
      Lee, Sangmin  and
      Hun Han, Seung  and
      Park, Saeran  and
      Lee, Jiyoon  and
      Jeong, Kiyoon  and
      Kang, Pilsung",
    editor = {Deutsch, Daniel  and
      Dror, Rotem  and
      Eger, Steffen  and
      Gao, Yang  and
      Leiter, Christoph  and
      Opitz, Juri  and
      R{\"u}ckl{\'e}, Andreas},
    booktitle = "Proceedings of the 4th Workshop on Evaluation and Comparison of NLP Systems",
    month = nov,
    year = "2023",
    address = "Bali, Indonesia",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-old-resolve/2023.eval4nlp-1.14/",
    doi = "10.18653/v1/2023.eval4nlp-1.14",
    pages = "164--183"
}
@inproceedings{lu-lin-2023-characterised,
    title = "Characterised {LLM}s Affect its Evaluation of Summary and Translation",
    author = "Lu, Yu-An  and
      Lin, Yu-Ting",
    editor = {Deutsch, Daniel  and
      Dror, Rotem  and
      Eger, Steffen  and
      Gao, Yang  and
      Leiter, Christoph  and
      Opitz, Juri  and
      R{\"u}ckl{\'e}, Andreas},
    booktitle = "Proceedings of the 4th Workshop on Evaluation and Comparison of NLP Systems",
    month = nov,
    year = "2023",
    address = "Bali, Indonesia",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-old-resolve/2023.eval4nlp-1.15/",
    doi = "10.18653/v1/2023.eval4nlp-1.15",
    pages = "184--192"
}
@inproceedings{akkasi-etal-2023-reference,
    title = "Reference-Free Summarization Evaluation with Large Language Models",
    author = "Akkasi, Abbas  and
      Fraser, Kathleen  and
      Komeili, Majid",
    editor = {Deutsch, Daniel  and
      Dror, Rotem  and
      Eger, Steffen  and
      Gao, Yang  and
      Leiter, Christoph  and
      Opitz, Juri  and
      R{\"u}ckl{\'e}, Andreas},
    booktitle = "Proceedings of the 4th Workshop on Evaluation and Comparison of NLP Systems",
    month = nov,
    year = "2023",
    address = "Bali, Indonesia",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-old-resolve/2023.eval4nlp-1.16/",
    doi = "10.18653/v1/2023.eval4nlp-1.16",
    pages = "193--201"
}
@inproceedings{kotonya-etal-2023-little,
    title = "Little Giants: Exploring the Potential of Small {LLM}s as Evaluation Metrics in Summarization in the {E}val4{NLP} 2023 Shared Task",
    author = "Kotonya, Neema  and
      Krishnasamy, Saran  and
      Tetreault, Joel  and
      Jaimes, Alejandro",
    editor = {Deutsch, Daniel  and
      Dror, Rotem  and
      Eger, Steffen  and
      Gao, Yang  and
      Leiter, Christoph  and
      Opitz, Juri  and
      R{\"u}ckl{\'e}, Andreas},
    booktitle = "Proceedings of the 4th Workshop on Evaluation and Comparison of NLP Systems",
    month = nov,
    year = "2023",
    address = "Bali, Indonesia",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-old-resolve/2023.eval4nlp-1.17/",
    doi = "10.18653/v1/2023.eval4nlp-1.17",
    pages = "202--218"
}
@inproceedings{mahmoudi-2023-exploring,
    title = "Exploring Prompting Large Language Models as Explainable Metrics",
    author = "Mahmoudi, Ghazaleh",
    editor = {Deutsch, Daniel  and
      Dror, Rotem  and
      Eger, Steffen  and
      Gao, Yang  and
      Leiter, Christoph  and
      Opitz, Juri  and
      R{\"u}ckl{\'e}, Andreas},
    booktitle = "Proceedings of the 4th Workshop on Evaluation and Comparison of NLP Systems",
    month = nov,
    year = "2023",
    address = "Bali, Indonesia",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-old-resolve/2023.eval4nlp-1.18/",
    doi = "10.18653/v1/2023.eval4nlp-1.18",
    pages = "219--227"
}
@inproceedings{larionov-etal-2023-team,
    title = "Team {NLLG} submission for {E}val4{NLP} 2023 Shared Task: Retrieval-Augmented In-Context Learning for {NLG} Evaluation",
    author = "Larionov, Daniil  and
      Viskov, Vasiliy  and
      Kokush, George  and
      Panchenko, Alexander  and
      Eger, Steffen",
    editor = {Deutsch, Daniel  and
      Dror, Rotem  and
      Eger, Steffen  and
      Gao, Yang  and
      Leiter, Christoph  and
      Opitz, Juri  and
      R{\"u}ckl{\'e}, Andreas},
    booktitle = "Proceedings of the 4th Workshop on Evaluation and Comparison of NLP Systems",
    month = nov,
    year = "2023",
    address = "Bali, Indonesia",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-old-resolve/2023.eval4nlp-1.19/",
    doi = "10.18653/v1/2023.eval4nlp-1.19",
    pages = "228--234"
}