{"total":40,"rows":[{"id":"2308.10149","title":"A Survey on Fairness in Large Language Models","created":"2023-08-20","cited_by_count":95,"area":null},{"id":"2107.06641","title":"Trustworthy AI: A Computational Perspective","created":"2021-07-12","cited_by_count":93,"area":null},{"id":"2106.11410","title":"A Survey of Race, Racism, and Anti-Racism in NLP","created":"2021-06-21","cited_by_count":75,"area":null},{"id":"2203.13928","title":"On the Intrinsic and Extrinsic Fairness Evaluation Metrics for Contextualized Language Representations","created":"2022-03-25","cited_by_count":75,"area":null},{"id":"2205.02526","title":"Theories of \"Gender\" in NLP Bias Research","created":"2022-05-05","cited_by_count":62,"area":null},{"id":"2202.00126","title":"Handling Bias in Toxic Speech Detection: A Survey","created":"2022-01-26","cited_by_count":61,"area":null},{"id":"2203.09192","title":"Entropy-based Attention Regularization Frees Unintended Bias Mitigation from Lists","created":"2022-03-17","cited_by_count":55,"area":null},{"id":"2209.10222","title":"Fairness Reprogramming","created":"2022-09-21","cited_by_count":33,"area":null},{"id":"2306.08158","title":"Sociodemographic Bias in Language Models: A Survey and Forward Path","created":"2023-06-13","cited_by_count":28,"area":null},{"id":"2211.11109","title":"Deep Learning on a Healthy Data Diet: Finding Important Examples for Fairness","created":"2022-11-20","cited_by_count":21,"area":null},{"id":"2305.14695","title":"A Causal View of Entity Bias in (Large) Language Models","created":"2023-05-24","cited_by_count":21,"area":null},{"id":"2106.10826","title":"Does Robustness Improve Fairness? Approaching Fairness with Word Substitution Robustness Methods for Text Classification","created":"2021-06-21","cited_by_count":20,"area":null},{"id":"2202.12690","title":"On Modality Bias Recognition and Reduction","created":"2022-02-25","cited_by_count":20,"area":null},{"id":"2105.02778","title":"The Authors Matter: Understanding and Mitigating Implicit Bias in Deep Text Classification","created":"2021-05-06","cited_by_count":18,"area":null},{"id":"2110.00911","title":"Enhancing Model Robustness and Fairness with Causality: A Regularization Approach","created":"2021-10-03","cited_by_count":11,"area":null},{"id":"2210.02659","title":"Explainable Abuse Detection as Intent Classification and Slot Filling","created":"2022-10-06","cited_by_count":11,"area":null},{"id":"2305.13088","title":"Should We Attend More or Less? Modulating Attention for Fairness","created":"2023-05-22","cited_by_count":11,"area":null},{"id":"2306.00198","title":"An Invariant Learning Characterization of Controlled Text Generation","created":"2023-05-31","cited_by_count":9,"area":null},{"id":"2205.09460","title":"Why only Micro-F1? Class Weighting of Measures for Relation Classification","created":"2022-05-19","cited_by_count":8,"area":null},{"id":"2406.00046","title":"Hate Speech Detection with Generalizable Target-aware Fairness","created":"2024-05-28","cited_by_count":7,"area":null},{"id":"2103.05345","title":"Detecting Inappropriate Messages on Sensitive Topics that Could Harm a Company's Reputation","created":"2021-03-09","cited_by_count":6,"area":null},{"id":"2505.12349","title":"Wisdom from Diversity: Bias Mitigation Through Hybrid Human-LLM Crowds","created":"2025-05-18","cited_by_count":6,"area":null},{"id":"2204.05459","title":"Easy Adaptation to Mitigate Gender Bias in Multilingual Text Classification","created":"2022-04-12","cited_by_count":5,"area":null},{"id":"2205.12391","title":"Toward Understanding Bias Correlations for Mitigation in NLP","created":"2022-05-24","cited_by_count":5,"area":null},{"id":"2209.09975","title":"Power of Explanations: Towards automatic debiasing in hate speech detection","created":"2022-09-07","cited_by_count":5,"area":null},{"id":"2511.14662","title":"Bias in, Bias out: Annotation Bias in Multilingual Large Language Models","created":"2025-11-18","cited_by_count":5,"area":null},{"id":"2407.08067","title":"On LLM Wizards: Identifying Large Language Models' Behaviors for Wizard of Oz Experiments","created":"2024-07-10","cited_by_count":4,"area":null},{"id":"2206.08445","title":"Enriching Abusive Language Detection with Community Context","created":"2022-06-16","cited_by_count":3,"area":null},{"id":"2206.08978","title":"Towards a Deep Multi-layered Dialectal Language Analysis: A Case Study of African-American English","created":"2022-06-03","cited_by_count":3,"area":null},{"id":"2311.09428","title":"Beyond Detection: Unveiling Fairness Vulnerabilities in Abusive Language Models","created":"2023-11-15","cited_by_count":3,"area":null},{"id":"2210.12233","title":"TCAB: A Large-Scale Text Classification Attack Benchmark","created":"2022-10-21","cited_by_count":2,"area":null},{"id":"2312.00434","title":"PEFTDebias : Capturing debiasing information using PEFTs","created":"2023-12-01","cited_by_count":2,"area":null},{"id":"2505.24538","title":"Don't Erase, Inform! Detecting and Contextualizing Harmful Language in Cultural Heritage Collections","created":"2025-05-30","cited_by_count":2,"area":null},{"id":"2202.03907","title":"Context-Aware Discrimination Detection in Job Vacancies using Computational Language Models","created":"2022-02-02","cited_by_count":1,"area":null},{"id":"2203.02392","title":"Beyond Plain Toxic: Detection of Inappropriate Statements on Flammable Topics for the Russian Language","created":"2022-03-04","cited_by_count":1,"area":null},{"id":"2502.13548","title":"Detecting Linguistic Bias in Government Documents Using Large language Models","created":"2025-02-19","cited_by_count":1,"area":null},{"id":"2506.22481","title":"Theories of \"Sexuality\" in Natural Language Processing Bias Research","created":"2025-06-22","cited_by_count":1,"area":null},{"id":"2511.00749","title":"Erasing 'Ugly' from the Internet: Propagation of the Beauty Myth in Text-Image Models","created":"2025-11-02","cited_by_count":1,"area":null},{"id":"2407.01697","title":"NLPGuard: A Framework for Mitigating the Use of Protected Attributes by NLP Classifiers","created":"2024-07-01","cited_by_count":0,"area":null},{"id":"2604.14970","title":"Explain the Flag: Contextualizing Hate Speech Beyond Censorship","created":"2026-04-16","cited_by_count":0,"area":null}],"next_cursor":null}