@proceedings{trustnlp-2024-trustworthy,
    title = "Proceedings of the 4th Workshop on Trustworthy Natural Language Processing (TrustNLP 2024)",
    editor = "Ovalle, Anaelia  and
      Chang, Kai-Wei  and
      Cao, Yang Trista  and
      Mehrabi, Ninareh  and
      Zhao, Jieyu  and
      Galstyan, Aram  and
      Dhamala, Jwala  and
      Kumar, Anoop  and
      Gupta, Rahul",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/manual-author-scripts/2024.trustnlp-1.0/"
}
@inproceedings{adilazuarda-2024-beyond,
    title = "Beyond {T}uring: A Comparative Analysis of Approaches for Detecting Machine-Generated Text",
    author = "Adilazuarda, Muhammad",
    editor = "Ovalle, Anaelia  and
      Chang, Kai-Wei  and
      Cao, Yang Trista  and
      Mehrabi, Ninareh  and
      Zhao, Jieyu  and
      Galstyan, Aram  and
      Dhamala, Jwala  and
      Kumar, Anoop  and
      Gupta, Rahul",
    booktitle = "Proceedings of the 4th Workshop on Trustworthy Natural Language Processing (TrustNLP 2024)",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/manual-author-scripts/2024.trustnlp-1.1/",
    doi = "10.18653/v1/2024.trustnlp-1.1",
    pages = "1--12"
}
@inproceedings{lal-etal-2024-automated,
    title = "Automated Adversarial Discovery for Safety Classifiers",
    author = "Lal, Yash Kumar  and
      Lahoti, Preethi  and
      Sinha, Aradhana  and
      Qin, Yao  and
      Balashankar, Ananth",
    editor = "Ovalle, Anaelia  and
      Chang, Kai-Wei  and
      Cao, Yang Trista  and
      Mehrabi, Ninareh  and
      Zhao, Jieyu  and
      Galstyan, Aram  and
      Dhamala, Jwala  and
      Kumar, Anoop  and
      Gupta, Rahul",
    booktitle = "Proceedings of the 4th Workshop on Trustworthy Natural Language Processing (TrustNLP 2024)",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/manual-author-scripts/2024.trustnlp-1.2/",
    doi = "10.18653/v1/2024.trustnlp-1.2",
    pages = "13--26"
}
@inproceedings{setzu-etal-2024-fairbelief,
    title = "{F}air{B}elief - Assessing Harmful Beliefs in Language Models",
    author = "Setzu, Mattia  and
      Marchiori Manerba, Marta  and
      Minervini, Pasquale  and
      Nozza, Debora",
    editor = "Ovalle, Anaelia  and
      Chang, Kai-Wei  and
      Cao, Yang Trista  and
      Mehrabi, Ninareh  and
      Zhao, Jieyu  and
      Galstyan, Aram  and
      Dhamala, Jwala  and
      Kumar, Anoop  and
      Gupta, Rahul",
    booktitle = "Proceedings of the 4th Workshop on Trustworthy Natural Language Processing (TrustNLP 2024)",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/manual-author-scripts/2024.trustnlp-1.3/",
    doi = "10.18653/v1/2024.trustnlp-1.3",
    pages = "27--39"
}
@inproceedings{bui-von-der-wense-2024-trade,
    title = "The Trade-off between Performance, Efficiency, and Fairness in Adapter Modules for Text Classification",
    author = "Bui, Minh Duc  and
      Von Der Wense, Katharina",
    editor = "Ovalle, Anaelia  and
      Chang, Kai-Wei  and
      Cao, Yang Trista  and
      Mehrabi, Ninareh  and
      Zhao, Jieyu  and
      Galstyan, Aram  and
      Dhamala, Jwala  and
      Kumar, Anoop  and
      Gupta, Rahul",
    booktitle = "Proceedings of the 4th Workshop on Trustworthy Natural Language Processing (TrustNLP 2024)",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/manual-author-scripts/2024.trustnlp-1.4/",
    doi = "10.18653/v1/2024.trustnlp-1.4",
    pages = "40--50"
}
@inproceedings{bohacek-bravansky-2024-xgboost,
    title = "When {XGB}oost Outperforms {GPT}-4 on Text Classification: A Case Study",
    author = "Bohacek, Matyas  and
      Bravansky, Michal",
    editor = "Ovalle, Anaelia  and
      Chang, Kai-Wei  and
      Cao, Yang Trista  and
      Mehrabi, Ninareh  and
      Zhao, Jieyu  and
      Galstyan, Aram  and
      Dhamala, Jwala  and
      Kumar, Anoop  and
      Gupta, Rahul",
    booktitle = "Proceedings of the 4th Workshop on Trustworthy Natural Language Processing (TrustNLP 2024)",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/manual-author-scripts/2024.trustnlp-1.5/",
    doi = "10.18653/v1/2024.trustnlp-1.5",
    pages = "51--60"
}
@inproceedings{lin-etal-2024-towards,
    title = "Towards Healthy {AI}: Large Language Models Need Therapists Too",
    author = "Lin, Baihan  and
      Bouneffouf, Djallel  and
      Cecchi, Guillermo  and
      Varshney, Kush",
    editor = "Ovalle, Anaelia  and
      Chang, Kai-Wei  and
      Cao, Yang Trista  and
      Mehrabi, Ninareh  and
      Zhao, Jieyu  and
      Galstyan, Aram  and
      Dhamala, Jwala  and
      Kumar, Anoop  and
      Gupta, Rahul",
    booktitle = "Proceedings of the 4th Workshop on Trustworthy Natural Language Processing (TrustNLP 2024)",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/manual-author-scripts/2024.trustnlp-1.6/",
    doi = "10.18653/v1/2024.trustnlp-1.6",
    pages = "61--70"
}
@inproceedings{yoo-etal-2024-exploring,
    title = "Exploring Causal Mechanisms for Machine Text Detection Methods",
    author = "Yoo, Kiyoon  and
      Ahn, Wonhyuk  and
      Song, Yeji  and
      Kwak, Nojun",
    editor = "Ovalle, Anaelia  and
      Chang, Kai-Wei  and
      Cao, Yang Trista  and
      Mehrabi, Ninareh  and
      Zhao, Jieyu  and
      Galstyan, Aram  and
      Dhamala, Jwala  and
      Kumar, Anoop  and
      Gupta, Rahul",
    booktitle = "Proceedings of the 4th Workshop on Trustworthy Natural Language Processing (TrustNLP 2024)",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/manual-author-scripts/2024.trustnlp-1.7/",
    doi = "10.18653/v1/2024.trustnlp-1.7",
    pages = "71--78"
}
@inproceedings{rashad-etal-2024-factalign,
    title = "{F}act{A}lign: Fact-Level Hallucination Detection and Classification Through Knowledge Graph Alignment",
    author = "Rashad, Mohamed  and
      Zahran, Ahmed  and
      Amin, Abanoub  and
      Abdelaal, Amr  and
      Altantawy, Mohamed",
    editor = "Ovalle, Anaelia  and
      Chang, Kai-Wei  and
      Cao, Yang Trista  and
      Mehrabi, Ninareh  and
      Zhao, Jieyu  and
      Galstyan, Aram  and
      Dhamala, Jwala  and
      Kumar, Anoop  and
      Gupta, Rahul",
    booktitle = "Proceedings of the 4th Workshop on Trustworthy Natural Language Processing (TrustNLP 2024)",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/manual-author-scripts/2024.trustnlp-1.8/",
    doi = "10.18653/v1/2024.trustnlp-1.8",
    pages = "79--84"
}
@inproceedings{fu-etal-2024-cross,
    title = "Cross-Task Defense: Instruction-Tuning {LLM}s for Content Safety",
    author = "Fu, Yu  and
      Xiao, Wen  and
      Chen, Jia  and
      Li, Jiachen  and
      Papalexakis, Evangelos  and
      Chien, Aichi  and
      Dong, Yue",
    editor = "Ovalle, Anaelia  and
      Chang, Kai-Wei  and
      Cao, Yang Trista  and
      Mehrabi, Ninareh  and
      Zhao, Jieyu  and
      Galstyan, Aram  and
      Dhamala, Jwala  and
      Kumar, Anoop  and
      Gupta, Rahul",
    booktitle = "Proceedings of the 4th Workshop on Trustworthy Natural Language Processing (TrustNLP 2024)",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/manual-author-scripts/2024.trustnlp-1.9/",
    doi = "10.18653/v1/2024.trustnlp-1.9",
    pages = "85--93"
}
@inproceedings{brandl-etal-2024-interplay,
    title = "On the Interplay between Fairness and Explainability",
    author = "Brandl, Stephanie  and
      Bugliarello, Emanuele  and
      Chalkidis, Ilias",
    editor = "Ovalle, Anaelia  and
      Chang, Kai-Wei  and
      Cao, Yang Trista  and
      Mehrabi, Ninareh  and
      Zhao, Jieyu  and
      Galstyan, Aram  and
      Dhamala, Jwala  and
      Kumar, Anoop  and
      Gupta, Rahul",
    booktitle = "Proceedings of the 4th Workshop on Trustworthy Natural Language Processing (TrustNLP 2024)",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/manual-author-scripts/2024.trustnlp-1.10/",
    doi = "10.18653/v1/2024.trustnlp-1.10",
    pages = "94--108"
}
@inproceedings{cecchini-etal-2024-holistic,
    title = "Holistic Evaluation of Large Language Models: Assessing Robustness, Accuracy, and Toxicity for Real-World Applications",
    author = "Cecchini, David  and
      Nazir, Arshaan  and
      Chakravarthy, Kalyan  and
      Kocaman, Veysel",
    editor = "Ovalle, Anaelia  and
      Chang, Kai-Wei  and
      Cao, Yang Trista  and
      Mehrabi, Ninareh  and
      Zhao, Jieyu  and
      Galstyan, Aram  and
      Dhamala, Jwala  and
      Kumar, Anoop  and
      Gupta, Rahul",
    booktitle = "Proceedings of the 4th Workshop on Trustworthy Natural Language Processing (TrustNLP 2024)",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/manual-author-scripts/2024.trustnlp-1.11/",
    doi = "10.18653/v1/2024.trustnlp-1.11",
    pages = "109--117"
}
@inproceedings{fang-etal-2024-hgot,
    title = "{HGOT}: Hierarchical Graph of Thoughts for Retrieval-Augmented In-Context Learning in Factuality Evaluation",
    author = "Fang, Yihao  and
      Thomas, Stephen  and
      Zhu, Xiaodan",
    editor = "Ovalle, Anaelia  and
      Chang, Kai-Wei  and
      Cao, Yang Trista  and
      Mehrabi, Ninareh  and
      Zhao, Jieyu  and
      Galstyan, Aram  and
      Dhamala, Jwala  and
      Kumar, Anoop  and
      Gupta, Rahul",
    booktitle = "Proceedings of the 4th Workshop on Trustworthy Natural Language Processing (TrustNLP 2024)",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/manual-author-scripts/2024.trustnlp-1.12/",
    doi = "10.18653/v1/2024.trustnlp-1.12",
    pages = "118--144"
}
@inproceedings{groot-valdenegro-toro-2024-overconfidence,
    title = "Overconfidence is Key: Verbalized Uncertainty Evaluation in Large Language and Vision-Language Models",
    author = "Groot, Tobias  and
      Valdenegro - Toro, Matias",
    editor = "Ovalle, Anaelia  and
      Chang, Kai-Wei  and
      Cao, Yang Trista  and
      Mehrabi, Ninareh  and
      Zhao, Jieyu  and
      Galstyan, Aram  and
      Dhamala, Jwala  and
      Kumar, Anoop  and
      Gupta, Rahul",
    booktitle = "Proceedings of the 4th Workshop on Trustworthy Natural Language Processing (TrustNLP 2024)",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/manual-author-scripts/2024.trustnlp-1.13/",
    doi = "10.18653/v1/2024.trustnlp-1.13",
    pages = "145--171"
}
@inproceedings{patel-etal-2024-tweak,
    title = "Tweak to Trust: Assessing the Reliability of Summarization Metrics in Contact Centers via Perturbed Summaries",
    author = "Patel, Kevin  and
      Agrawal, Suraj  and
      Kumar, Ayush",
    editor = "Ovalle, Anaelia  and
      Chang, Kai-Wei  and
      Cao, Yang Trista  and
      Mehrabi, Ninareh  and
      Zhao, Jieyu  and
      Galstyan, Aram  and
      Dhamala, Jwala  and
      Kumar, Anoop  and
      Gupta, Rahul",
    booktitle = "Proceedings of the 4th Workshop on Trustworthy Natural Language Processing (TrustNLP 2024)",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/manual-author-scripts/2024.trustnlp-1.14/",
    doi = "10.18653/v1/2024.trustnlp-1.14",
    pages = "172--186"
}
@inproceedings{khalatbari-etal-2024-flatness,
    title = "Flatness-Aware Gradient Descent for Safe Conversational {AI}",
    author = "Khalatbari, Leila  and
      Hosseini, Saeid  and
      Sameti, Hossein  and
      Fung, Pascale",
    editor = "Ovalle, Anaelia  and
      Chang, Kai-Wei  and
      Cao, Yang Trista  and
      Mehrabi, Ninareh  and
      Zhao, Jieyu  and
      Galstyan, Aram  and
      Dhamala, Jwala  and
      Kumar, Anoop  and
      Gupta, Rahul",
    booktitle = "Proceedings of the 4th Workshop on Trustworthy Natural Language Processing (TrustNLP 2024)",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/manual-author-scripts/2024.trustnlp-1.15/",
    doi = "10.18653/v1/2024.trustnlp-1.15",
    pages = "187--195"
}
@inproceedings{cao-etal-2024-introducing,
    title = "Introducing {G}en{C}eption for Multimodal {LLM} Benchmarking: You May Bypass Annotations",
    author = "Cao, Lele  and
      Buchner, Valentin  and
      Senane, Zineb  and
      Yang, Fangkai",
    editor = "Ovalle, Anaelia  and
      Chang, Kai-Wei  and
      Cao, Yang Trista  and
      Mehrabi, Ninareh  and
      Zhao, Jieyu  and
      Galstyan, Aram  and
      Dhamala, Jwala  and
      Kumar, Anoop  and
      Gupta, Rahul",
    booktitle = "Proceedings of the 4th Workshop on Trustworthy Natural Language Processing (TrustNLP 2024)",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/manual-author-scripts/2024.trustnlp-1.16/",
    doi = "10.18653/v1/2024.trustnlp-1.16",
    pages = "196--201"
}
@inproceedings{gao-etal-2024-semantic,
    title = "Semantic-Preserving Adversarial Example Attack against {BERT}",
    author = "Gao, Chongyang  and
      Gu, Kang  and
      Vosoughi, Soroush  and
      Mehnaz, Shagufta",
    editor = "Ovalle, Anaelia  and
      Chang, Kai-Wei  and
      Cao, Yang Trista  and
      Mehrabi, Ninareh  and
      Zhao, Jieyu  and
      Galstyan, Aram  and
      Dhamala, Jwala  and
      Kumar, Anoop  and
      Gupta, Rahul",
    booktitle = "Proceedings of the 4th Workshop on Trustworthy Natural Language Processing (TrustNLP 2024)",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/manual-author-scripts/2024.trustnlp-1.17/",
    doi = "10.18653/v1/2024.trustnlp-1.17",
    pages = "202--207"
}
@inproceedings{upadhayay-behzadan-2024-sandwich,
    title = "Sandwich attack: Multi-language Mixture Adaptive Attack on {LLM}s",
    author = "Upadhayay, Bibek  and
      Behzadan, Vahid",
    editor = "Ovalle, Anaelia  and
      Chang, Kai-Wei  and
      Cao, Yang Trista  and
      Mehrabi, Ninareh  and
      Zhao, Jieyu  and
      Galstyan, Aram  and
      Dhamala, Jwala  and
      Kumar, Anoop  and
      Gupta, Rahul",
    booktitle = "Proceedings of the 4th Workshop on Trustworthy Natural Language Processing (TrustNLP 2024)",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/manual-author-scripts/2024.trustnlp-1.18/",
    doi = "10.18653/v1/2024.trustnlp-1.18",
    pages = "208--226"
}
@inproceedings{yang-etal-2024-masking,
    title = "Masking Latent Gender Knowledge for Debiasing Image Captioning",
    author = "Yang, Fan  and
      Ghosh, Shalini  and
      Barut, Emre  and
      Qin, Kechen  and
      Wanigasekara, Prashan  and
      Su, Chengwei  and
      Ruan, Weitong  and
      Gupta, Rahul",
    editor = "Ovalle, Anaelia  and
      Chang, Kai-Wei  and
      Cao, Yang Trista  and
      Mehrabi, Ninareh  and
      Zhao, Jieyu  and
      Galstyan, Aram  and
      Dhamala, Jwala  and
      Kumar, Anoop  and
      Gupta, Rahul",
    booktitle = "Proceedings of the 4th Workshop on Trustworthy Natural Language Processing (TrustNLP 2024)",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/manual-author-scripts/2024.trustnlp-1.19/",
    doi = "10.18653/v1/2024.trustnlp-1.19",
    pages = "227--238"
}
@inproceedings{bauer-etal-2024-believe,
    title = "{BELIEVE}: Belief-Enhanced Instruction Generation and Augmentation for Zero-Shot Bias Mitigation",
    author = "Bauer, Lisa  and
      Mehrabi, Ninareh  and
      Goyal, Palash  and
      Chang, Kai-Wei  and
      Galstyan, Aram  and
      Gupta, Rahul",
    editor = "Ovalle, Anaelia  and
      Chang, Kai-Wei  and
      Cao, Yang Trista  and
      Mehrabi, Ninareh  and
      Zhao, Jieyu  and
      Galstyan, Aram  and
      Dhamala, Jwala  and
      Kumar, Anoop  and
      Gupta, Rahul",
    booktitle = "Proceedings of the 4th Workshop on Trustworthy Natural Language Processing (TrustNLP 2024)",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/manual-author-scripts/2024.trustnlp-1.20/",
    doi = "10.18653/v1/2024.trustnlp-1.20",
    pages = "239--251"
}
@inproceedings{zarharan-etal-2024-tell,
    title = "Tell Me Why: Explainable Public Health Fact-Checking with Large Language Models",
    author = "Zarharan, Majid  and
      Wullschleger, Pascal  and
      Behkam Kia, Babak  and
      Pilehvar, Mohammad Taher  and
      Foster, Jennifer",
    editor = "Ovalle, Anaelia  and
      Chang, Kai-Wei  and
      Cao, Yang Trista  and
      Mehrabi, Ninareh  and
      Zhao, Jieyu  and
      Galstyan, Aram  and
      Dhamala, Jwala  and
      Kumar, Anoop  and
      Gupta, Rahul",
    booktitle = "Proceedings of the 4th Workshop on Trustworthy Natural Language Processing (TrustNLP 2024)",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/manual-author-scripts/2024.trustnlp-1.21/",
    doi = "10.18653/v1/2024.trustnlp-1.21",
    pages = "252--278"
}