{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T04:08:13Z","timestamp":1750824493265,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":78,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,23]]},"DOI":"10.1145\/3715275.3732192","type":"proceedings-article","created":{"date-parts":[[2025,6,23]],"date-time":"2025-06-23T17:03:13Z","timestamp":1750698193000},"page":"3006-3029","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Gender Bias in Explainability: Investigating Performance Disparity in Post-hoc Methods"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7831-3141","authenticated-orcid":false,"given":"Mahdi","family":"Dhaini","sequence":"first","affiliation":[{"name":"School of Computation, Information and Technology, Department of Computer Science, Technical University of Munich, Munich, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6170-3541","authenticated-orcid":false,"given":"Ege","family":"Erdogan","sequence":"additional","affiliation":[{"name":"School of Computation, Information and Technology, Department of Computer Science, Technical University of Munich, Munich, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7408-7483","authenticated-orcid":false,"given":"Nils","family":"Feldhus","sequence":"additional","affiliation":[{"name":"BIFOLD-Berlin Institute for the Foundations of Learning and Data, German Research Center for Artificial Intelligence (DFKI), TU Berlin, BIFOLD, DFKI, Berlin, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3123-7268","authenticated-orcid":false,"given":"Gjergji","family":"Kasneci","sequence":"additional","affiliation":[{"name":"School of Computation, Information and Technology, Department of Computer Science, Technical University of Munich, Munich, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,6,23]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"2025. Definition of STAKEHOLDERS. https:\/\/www.merriam-webster.com\/dictionary\/stakeholders"},{"key":"e_1_3_3_2_3_2","unstructured":"David Alvarez-Melis and Tommi\u00a0S. Jaakkola. 2018. On the Robustness of Interpretability Methods. arxiv:https:\/\/arXiv.org\/abs\/1806.08049\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/1806.08049"},{"key":"e_1_3_3_2_4_2","unstructured":"Julia Angwin Jeff Larson Lauren Kirchner and Surya Mattu. 2016. Machine bias. https:\/\/www.propublica.org\/article\/machine-bias-risk-assessments-in-criminal-sentencing"},{"key":"e_1_3_3_2_5_2","unstructured":"AI Anthropic. 2024. The claude 3 model family: Opus sonnet haiku. Claude-3 Model Card 1 (2024)."},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"publisher","unstructured":"Leila Arras Ahmed Osman and Wojciech Samek. 2022. CLEVR-XAI: A benchmark dataset for the ground truth evaluation of neural network explanations. Information Fusion 81 (2022) 14\u201340. https:\/\/doi.org\/10.1016\/j.inffus.2021.11.008","DOI":"10.1016\/j.inffus.2021.11.008"},{"key":"e_1_3_3_2_7_2","volume-title":"Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations","author":"Attanasio Giuseppe","year":"2023","unstructured":"Giuseppe Attanasio, Eliana Pastor, Chiara Di\u00a0Bonaventura, and Debora Nozza. 2023. ferret: a Framework for Benchmarking Explainers on Transformers. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations. Association for Computational Linguistics."},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3533179"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.trustnlp-1.8"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"crossref","unstructured":"Milan Bhan Jean-Noel Vittaut Nicolas Chesneau and Marie-Jeanne Lesot. 2024. Self-AMPLIFY: Improving Small Language Models with Self Post Hoc Explanations. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2402.12038 (2024).","DOI":"10.18653\/v1\/2024.emnlp-main.615"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.485"},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.81"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.trustnlp-1.10"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.477"},{"key":"e_1_3_3_2_15_2","unstructured":"Council of European Union. 2024. Council regulation (EU) no 2024\/1689. https:\/\/eur-lex.europa.eu\/legal-content\/EN\/TXT\/?uri=CELEX:32024R1689."},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3514094.3534159"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.aacl-main.46"},{"key":"e_1_3_3_2_18_2","unstructured":"Bj\u00f6rn Deiseroth Mayukh Deb Samuel Weinbach Manuel Brack Patrick Schramowski and Kristian Kersting. 2023. AtMan: Understanding Transformer Predictions Through Memory Efficient Attention Manipulation. arxiv:https:\/\/arXiv.org\/abs\/2301.08110\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2301.08110"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1423"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.408"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.inlg-main.49"},{"key":"e_1_3_3_2_22_2","unstructured":"Xi Fang Weijie Xu Fiona Anting\u00a0Tan Jiani Zhang Ziqing Hu Yanjun Qi Scott Nickleach Diego Socolinsky Srinivasan Sengamedu and Christos Faloutsos. 2024. Large language models on tabular data\u2013a survey. arXiv e-prints (2024) arXiv\u20132402."},{"key":"e_1_3_3_2_23_2","unstructured":"Isabel\u00a0O Gallegos Ryan\u00a0A Rossi Joe Barrow Md\u00a0Mehrab Tanjim Sungchul Kim Franck Dernoncourt Tong Yu Ruiyi Zhang and Nesreen\u00a0K Ahmed. 2024. Bias and fairness in large language models: A survey. Computational Linguistics (2024) 1\u201379."},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","unstructured":"Amirata Ghorbani Abubakar Abid and James Zou. 2019. Interpretation of Neural Networks Is Fragile. Proceedings of the AAAI Conference on Artificial Intelligence 33 01 (Jul. 2019) 3681\u20133688. https:\/\/doi.org\/10.1609\/aaai.v33i01.33013681","DOI":"10.1609\/aaai.v33i01.33013681"},{"key":"e_1_3_3_2_25_2","first-page":"1322","volume-title":"Findings of the Association for Computational Linguistics: EACL 2024","author":"Hsia Jennifer","year":"2024","unstructured":"Jennifer Hsia, Danish Pruthi, Aarti Singh, and Zachary Lipton. 2024. Goodhart\u2018s Law Applies to NLP\u2018s Explanation Benchmarks. In Findings of the Association for Computational Linguistics: EACL 2024, Yvette Graham and Matthew Purver (Eds.). Association for Computational Linguistics, St. Julian\u2019s, Malta, 1322\u20131335. https:\/\/aclanthology.org\/2024.findings-eacl.88\/"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO58844.2023.10289865"},{"key":"e_1_3_3_2_27_2","unstructured":"Alon Jacovi. 2023. Trends in Explainable AI (XAI) Literature. arxiv:https:\/\/arXiv.org\/abs\/2301.05433\u00a0[cs.AI] https:\/\/arxiv.org\/abs\/2301.05433"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.386"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1357"},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.gebnlp-1.20"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/3442188.3445941"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.372"},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"publisher","unstructured":"Shreya Johri Jaehwan Jeong Benjamin\u00a0A Tran Daniel\u00a0I Schlessinger Shannon Wongvibulsin Leandra\u00a0A Barnes Hong-Yu Zhou Zhuo\u00a0Ran Cai Eliezer\u00a0M Van\u00a0Allen David Kim et\u00a0al. 2025. An evaluation framework for clinical use of large language models in patient interaction tasks. Nature Medicine (2025) 1\u201310. https:\/\/doi.org\/10.1038\/s41591-024-03328-5","DOI":"10.1038\/s41591-024-03328-5"},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.474"},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"crossref","unstructured":"Satyapriya Krishna Tessa Han Alex Gu Steven Wu Shahin Jabbari and Himabindu Lakkaraju. 2024. The Disagreement Problem in Explainable Machine Learning: A Practitioner\u2019s Perspective. Transactions on Machine Learning Research (2024). https:\/\/openreview.net\/forum?id=jESY2WTZCe","DOI":"10.21203\/rs.3.rs-2963888\/v1"},{"key":"e_1_3_3_2_36_2","series-title":"(NIPS \u201923)","volume-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems","author":"Krishna Satyapriya","year":"2024","unstructured":"Satyapriya Krishna, Jiaqi Ma, Dylan Slack, Asma Ghandeharioun, Sameer Singh, and Himabindu Lakkaraju. 2024. Post hoc explanations of language models can improve language models. In Proceedings of the 37th International Conference on Neural Information Processing Systems (New Orleans, LA, USA) (NIPS \u201923). Curran Associates Inc., Red Hook, NY, USA, Article 2857, 16\u00a0pages."},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1145\/3375627.3375833"},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"publisher","unstructured":"Markus Langer Daniel Oster Timo Speith Holger Hermanns Lena K\u00e4stner Eva Schmidt Andreas Sesing and Kevin Baum. 2021. What do we want from Explainable Artificial Intelligence (XAI)? \u2013 A stakeholder perspective on XAI and a conceptual model guiding interdisciplinary XAI research. Artificial Intelligence 296 (2021) 103473. https:\/\/doi.org\/10.1016\/j.artint.2021.103473","DOI":"10.1016\/j.artint.2021.103473"},{"key":"e_1_3_3_2_39_2","unstructured":"Tobias Leemann Alina Fastowski Felix Pfeiffer and Gjergji Kasneci. 2025. Attention Mechanisms Don\u2019t Learn Additive Models: Rethinking Feature Importance for Transformers. arxiv:https:\/\/arXiv.org\/abs\/2405.13536\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2405.13536"},{"key":"e_1_3_3_2_40_2","first-page":"1630","volume-title":"Advances in Neural Information Processing Systems","author":"Li Xuhong","year":"2023","unstructured":"Xuhong Li, Mengnan Du, Jiamin Chen, Yekun Chai, Himabindu Lakkaraju, and Haoyi Xiong. 2023. M4: A Unified XAI Benchmark for Faithfulness Evaluation of Feature Attribution Methods across Metrics, Modalities and Models. In Advances in Neural Information Processing Systems, A.\u00a0Oh, T.\u00a0Naumann, A.\u00a0Globerson, K.\u00a0Saenko, M.\u00a0Hardt, and S.\u00a0Levine (Eds.), Vol.\u00a036. Curran Associates, Inc., 1630\u20131643. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2023\/file\/05957c194f4c77ac9d91e1374d2def6b-Paper-Datasets_and_Benchmarks.pdf"},{"key":"e_1_3_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1560"},{"key":"e_1_3_3_2_42_2","unstructured":"Yinhan Liu Myle Ott Naman Goyal Jingfei Du Mandar Joshi Danqi Chen Omer Levy Mike Lewis Luke Zettlemoyer and Veselin Stoyanov. 2019. RoBERTa: A Robustly Optimized BERT Pretraining Approach. CoRR abs\/1907.11692 (2019). arxiv:https:\/\/arXiv.org\/abs\/1907.11692http:\/\/arxiv.org\/abs\/1907.11692"},{"key":"e_1_3_3_2_43_2","doi-asserted-by":"publisher","unstructured":"Luca Longo Mario Brcic Federico Cabitza Jaesik Choi Roberto Confalonieri Javier\u00a0Del Ser Riccardo Guidotti Yoichi Hayashi Francisco Herrera Andreas Holzinger Richard Jiang Hassan Khosravi Freddy Lecue Gianclaudio Malgieri Andr\u00e9s P\u00e1ez Wojciech Samek Johannes Schneider Timo Speith and Simone Stumpf. 2024. Explainable Artificial Intelligence (XAI) 2.0: A manifesto of open challenges and interdisciplinary research directions. Information Fusion 106 (2024) 102301. https:\/\/doi.org\/10.1016\/j.inffus.2024.102301","DOI":"10.1016\/j.inffus.2024.102301"},{"key":"e_1_3_3_2_44_2","unstructured":"I Loshchilov. 2017. Decoupled weight decay regularization. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1711.05101 (2017)."},{"key":"e_1_3_3_2_45_2","unstructured":"Scott\u00a0M Lundberg and Su-In Lee. 2017. A unified approach to interpreting model predictions. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_3_2_46_2","doi-asserted-by":"publisher","unstructured":"Qing Lyu Marianna Apidianaki and Chris Callison-Burch. 2024. Towards Faithful Model Explanation in NLP: A Survey. Computational Linguistics 50 2 (June 2024) 657\u2013723. https:\/\/doi.org\/10.1162\/colia00511","DOI":"10.1162\/colia00511"},{"key":"e_1_3_3_2_47_2","unstructured":"Aleksander Madry. 2017. Towards deep learning models resistant to adversarial attacks. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1706.06083 (2017)."},{"key":"e_1_3_3_2_48_2","unstructured":"Andreas Madsen Himabindu Lakkaraju Siva Reddy and Sarath Chandar. 2024. Interpretability Needs a New Paradigm. arxiv:https:\/\/arXiv.org\/abs\/2405.05386\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2405.05386"},{"key":"e_1_3_3_2_49_2","doi-asserted-by":"publisher","unstructured":"Andreas Madsen Siva Reddy and Sarath Chandar. 2022. Post-hoc Interpretability for Neural NLP: A Survey. ACM Comput. Surv. 55 8 Article 155 (Dec. 2022) 42\u00a0pages. https:\/\/doi.org\/10.1145\/3546577","DOI":"10.1145\/3546577"},{"key":"e_1_3_3_2_50_2","doi-asserted-by":"publisher","unstructured":"Binny Mathew Punyajoy Saha Seid\u00a0Muhie Yimam Chris Biemann Pawan Goyal and Animesh Mukherjee. 2021. HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection. Proceedings of the AAAI Conference on Artificial Intelligence 35 17 (May 2021) 14867\u201314875. https:\/\/doi.org\/10.1609\/aaai.v35i17.17745","DOI":"10.1609\/aaai.v35i17.17745"},{"key":"e_1_3_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1145\/3630106.3659043"},{"key":"e_1_3_3_2_52_2","doi-asserted-by":"publisher","unstructured":"Katelyn Morrison Philipp Spitzer Violet Turri Michelle Feng Niklas K\u00fchl and Adam Perer. 2024. The Impact of Imperfect XAI on Human-AI Decision-Making. Proc. ACM Hum.-Comput. Interact. 8 CSCW1 Article 183 (April 2024) 39\u00a0pages. https:\/\/doi.org\/10.1145\/3641022","DOI":"10.1145\/3641022"},{"key":"e_1_3_3_2_53_2","first-page":"4593","volume-title":"Proceedings of the 29th International Conference on Computational Linguistics","author":"Mosca Edoardo","year":"2022","unstructured":"Edoardo Mosca, Ferenc Szigeti, Stella Tragianni, Daniel Gallagher, and Georg Groh. 2022. SHAP-Based Explanation Methods: A Review for NLP Interpretability. In Proceedings of the 29th International Conference on Computational Linguistics, Nicoletta Calzolari, Chu-Ren Huang, Hansaem Kim, James Pustejovsky, Leo Wanner, Key-Sun Choi, Pum-Mo Ryu, Hsin-Hsi Chen, Lucia Donatelli, Heng Ji, Sadao Kurohashi, Patrizia Paggio, Nianwen Xue, Seokhwan Kim, Younggyun Hahm, Zhong He, Tony\u00a0Kyungil Lee, Enrico Santus, Francis Bond, and Seung-Hoon Na (Eds.). International Committee on Computational Linguistics, Gyeongju, Republic of Korea, 4593\u20134603. https:\/\/aclanthology.org\/2022.coling-1.406\/"},{"key":"e_1_3_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.154"},{"key":"e_1_3_3_2_55_2","doi-asserted-by":"publisher","unstructured":"Meike Nauta Jan Trienes Shreyasi Pathak Elisa Nguyen Michelle Peters Yasmin Schmitt J\u00f6rg Schl\u00f6tterer Maurice van Keulen and Christin Seifert. 2023. From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI. ACM Comput. Surv. 55 13s Article 295 (jul 2023) 42\u00a0pages. https:\/\/doi.org\/10.1145\/3583558","DOI":"10.1145\/3583558"},{"key":"e_1_3_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.646"},{"key":"e_1_3_3_2_57_2","unstructured":"Alec Radford Jeffrey Wu Rewon Child David Luan Dario Amodei Ilya Sutskever et\u00a0al. 2019. Language models are unsupervised multitask learners. OpenAI blog 1 8 (2019) 9."},{"key":"e_1_3_3_2_58_2","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939778"},{"key":"e_1_3_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-90403-09"},{"key":"e_1_3_3_2_60_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-demo.40"},{"key":"e_1_3_3_2_61_2","doi-asserted-by":"crossref","unstructured":"Shlomo\u00a0S Sawilowsky. 2009. New effect size rules of thumb. Journal of modern applied statistical methods 8 (2009) 597\u2013599.","DOI":"10.22237\/jmasm\/1257035100"},{"key":"e_1_3_3_2_62_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642621"},{"key":"e_1_3_3_2_63_2","unstructured":"Karen Simonyan Andrea Vedaldi and Andrew Zisserman. 2013. Deep inside convolutional networks: Visualising image classification models and saliency maps. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1312.6034 (2013)."},{"key":"e_1_3_3_2_64_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-63787-2_23"},{"key":"e_1_3_3_2_65_2","first-page":"3319","volume-title":"International conference on machine learning","author":"Sundararajan Mukund","year":"2017","unstructured":"Mukund Sundararajan, Ankur Taly, and Qiqi Yan. 2017. Axiomatic attribution for deep networks. In International conference on machine learning. PMLR, 3319\u20133328."},{"key":"e_1_3_3_2_66_2","first-page":"16500","volume-title":"Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)","author":"T.y.s.s. Santosh","year":"2024","unstructured":"Santosh T.y.s.s., Nina Baumgartner, Matthias St\u00fcrmer, Matthias Grabmair, and Joel Niklaus. 2024. Towards Explainability and Fairness in Swiss Judgement Prediction: Benchmarking on a Multilingual Dataset. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), Nicoletta Calzolari, Min-Yen Kan, Veronique Hoste, Alessandro Lenci, Sakriani Sakti, and Nianwen Xue (Eds.). ELRA and ICCL, Torino, Italia, 16500\u201316513. https:\/\/aclanthology.org\/2024.lrec-main.1434"},{"key":"e_1_3_3_2_67_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.404"},{"key":"e_1_3_3_2_68_2","first-page":"12388","volume-title":"Advances in Neural Information Processing Systems","author":"Vig Jesse","year":"2020","unstructured":"Jesse Vig, Sebastian Gehrmann, Yonatan Belinkov, Sharon Qian, Daniel Nevo, Yaron Singer, and Stuart Shieber. 2020. Investigating Gender Bias in Language Models Using Causal Mediation Analysis. In Advances in Neural Information Processing Systems, H.\u00a0Larochelle, M.\u00a0Ranzato, R.\u00a0Hadsell, M.F. Balcan, and H.\u00a0Lin (Eds.), Vol.\u00a033. Curran Associates, Inc., 12388\u201312401. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2020\/file\/92650b2e92217715fe312e6fa7b90d82-Paper.pdf"},{"key":"e_1_3_3_2_69_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-tutorials.3"},{"key":"e_1_3_3_2_70_2","unstructured":"Rick Wilming Artur Dox Hjalmar Schulz Marta Oliveira Benedict Clark and Stefan Haufe. 2024. GECOBench: A Gender-Controlled Text Dataset and Benchmark for Quantifying Biases in Explanations. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.11547 (2024)."},{"key":"e_1_3_3_2_71_2","unstructured":"Alice Xiang and Inioluwa\u00a0Deborah Raji. 2019. On the Legal Compatibility of Fairness Definitions. arxiv:https:\/\/arXiv.org\/abs\/1912.00761\u00a0[cs.CY] https:\/\/arxiv.org\/abs\/1912.00761"},{"key":"e_1_3_3_2_72_2","unstructured":"Wenzhuo Yang Hung Le Tanmay Laud Silvio Savarese and Steven C.\u00a0H. Hoi. 2022. OmniXAI: A Library for Explainable AI. arxiv:https:\/\/arXiv.org\/abs\/2206.01612\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2206.01612"},{"key":"e_1_3_3_2_73_2","volume-title":"Advances in Neural Information Processing Systems","author":"Yeh Chih-Kuan","year":"2019","unstructured":"Chih-Kuan Yeh, Cheng-Yu Hsieh, Arun Suggala, David\u00a0I Inouye, and Pradeep\u00a0K Ravikumar. 2019. On the (In)fidelity and Sensitivity of Explanations. In Advances in Neural Information Processing Systems, H.\u00a0Wallach, H.\u00a0Larochelle, A.\u00a0Beygelzimer, F.\u00a0d'Alch\u00e9-Buc, E.\u00a0Fox, and R.\u00a0Garnett (Eds.), Vol.\u00a032. Curran Associates, Inc.https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2019\/file\/a7471fdc77b3435276507cc8f2dc2569-Paper.pdf"},{"key":"e_1_3_3_2_74_2","doi-asserted-by":"publisher","unstructured":"Haiyan Zhao Hanjie Chen Fan Yang Ninghao Liu Huiqi Deng Hengyi Cai Shuaiqiang Wang Dawei Yin and Mengnan Du. 2024. Explainability for Large Language Models: A Survey. ACM Trans. Intell. Syst. Technol. 15 2 Article 20 (Feb. 2024) 38\u00a0pages. https:\/\/doi.org\/10.1145\/3639372","DOI":"10.1145\/3639372"},{"key":"e_1_3_3_2_75_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2003"},{"key":"e_1_3_3_2_76_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.261"},{"key":"e_1_3_3_2_77_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.298"},{"key":"e_1_3_3_2_78_2","doi-asserted-by":"publisher","unstructured":"Jianlong Zhou Amir\u00a0H. Gandomi Fang Chen and Andreas Holzinger. 2021. Evaluating the Quality of Machine Learning Explanations: A Survey on Methods and Metrics. Electronics 10 5 (2021). https:\/\/doi.org\/10.3390\/electronics10050593","DOI":"10.3390\/electronics10050593"},{"key":"e_1_3_3_2_79_2","doi-asserted-by":"publisher","unstructured":"Julia\u00a0El Zini and Mariette Awad. 2022. On the Explainability of Natural Language Processing Deep Models. ACM Comput. Surv. 55 5 Article 103 (Dec. 2022) 31\u00a0pages. https:\/\/doi.org\/10.1145\/3529755","DOI":"10.1145\/3529755"}],"event":{"name":"FAccT '25: The 2025 ACM Conference on Fairness, Accountability, and Transparency","acronym":"FAccT '25","location":"Athens Greece"},"container-title":["Proceedings of the 2025 ACM Conference on Fairness, Accountability, and Transparency"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3715275.3732192","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,24]],"date-time":"2025-06-24T11:25:24Z","timestamp":1750764324000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3715275.3732192"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,23]]},"references-count":78,"alternative-id":["10.1145\/3715275.3732192","10.1145\/3715275"],"URL":"https:\/\/doi.org\/10.1145\/3715275.3732192","relation":{},"subject":[],"published":{"date-parts":[[2025,6,23]]},"assertion":[{"value":"2025-06-23","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}