{"total":42,"rows":[{"id":"2309.00770","title":"Bias and Fairness in Large Language Models: A Survey","created":"2023-09-02","cited_by_count":639,"area":null},{"id":"2305.12798","title":"Word Embeddings Are Steers for Language Models","created":"2023-05-22","cited_by_count":70,"area":null},{"id":"2402.12649","title":"Bias in Language Models: Beyond Trick Tests and Toward RUTEd Evaluation","created":"2024-02-20","cited_by_count":41,"area":null},{"id":"2407.03129","title":"Social Bias Evaluation for Large Language Models Requires Prompt Variations","created":"2024-07-03","cited_by_count":40,"area":null},{"id":"2210.14975","title":"MABEL: Attenuating Gender Bias using Textual Entailment Data","created":"2022-10-26","cited_by_count":31,"area":null},{"id":"2304.10153","title":"On the Independence of Association Bias and Empirical Fairness in Language Models","created":"2023-04-20","cited_by_count":29,"area":null},{"id":"2402.17954","title":"Twists, Humps, and Pebbles: Multilingual Speech Recognition Models Exhibit Gender Performance Gaps","created":"2024-02-28","cited_by_count":25,"area":null},{"id":"2407.10241","title":"BiasAlert: A Plug-and-play Tool for Social Bias Detection in LLMs","created":"2024-07-14","cited_by_count":21,"area":null},{"id":"2312.05662","title":"Understanding the Effect of Model Compression on Social Bias in Large Language Models","created":"2023-12-09","cited_by_count":19,"area":null},{"id":"2309.09697","title":"Evaluating Gender Bias of Pre-trained Language Models in Natural Language Inference by Considering All Labels","created":"2023-09-18","cited_by_count":16,"area":null},{"id":"2406.02378","title":"On the Intrinsic Self-Correction Capability of LLMs: Uncertainty and Latent Concept","created":"2024-06-04","cited_by_count":16,"area":null},{"id":"2310.12490","title":"Co$^2$PT: Mitigating Bias in Pre-trained Language Models through Counterfactual Contrastive Prompt Tuning","created":"2023-10-19","cited_by_count":15,"area":null},{"id":"2309.07251","title":"In-Contextual Gender Bias Suppression for Large Language Models","created":"2023-09-13","cited_by_count":12,"area":null},{"id":"2301.12074","title":"Comparing Intrinsic Gender Bias Evaluation Measures without using Human Annotated Examples","created":"2023-01-28","cited_by_count":8,"area":null},{"id":"2310.17530","title":"Evaluating Bias and Fairness in Gender-Neutral Pretrained Vision-and-Language Models","created":"2023-10-26","cited_by_count":6,"area":null},{"id":"2305.09281","title":"On the Origins of Bias in NLP through the Lens of the Jim Code","created":"2023-05-16","cited_by_count":5,"area":null},{"id":"2305.11789","title":"Solving NLP Problems through Human-System Collaboration: A Discussion-based Approach","created":"2023-05-19","cited_by_count":5,"area":null},{"id":"2401.08511","title":"The Gaps between Pre-train and Downstream Settings in Bias Evaluation and Debiasing","created":"2024-01-16","cited_by_count":5,"area":null},{"id":"2602.06181","title":"Investigating Social Bias Changes in Quantized Language Models","created":"2026-02-05","cited_by_count":5,"area":null},{"id":"2310.12936","title":"A Predictive Factor Analysis of Social Biases and Task-Performance in Pretrained Masked Language Models","created":"2023-10-19","cited_by_count":4,"area":null},{"id":"2311.12689","title":"Fair Text Classification with Wasserstein Independence","created":"2023-11-21","cited_by_count":4,"area":null},{"id":"2402.14258","title":"Eagle: Ethical Dataset Given from Real Interactions","created":"2024-02-22","cited_by_count":4,"area":null},{"id":"2406.05918","title":"Why Don't Prompt-Based Fairness Metrics Correlate?","created":"2024-06-09","cited_by_count":4,"area":null},{"id":"2407.01834","title":"A Study of Nationality Bias in Names and Perplexity using Off-the-Shelf Affect-related Tweet Classifiers","created":"2024-07-01","cited_by_count":4,"area":null},{"id":"2507.16557","title":"Exploring Gender Bias in Large Language Models: An In-depth Dive into the German Language","created":"2025-07-22","cited_by_count":3,"area":null},{"id":"2509.08146","title":"Bias after Prompting: Persistent Discrimination in Large Language Models","created":"2025-09-09","cited_by_count":3,"area":null},{"id":"2308.16549","title":"Thesis Distillation: Investigating The Impact of Bias in NLP Models on Hate Speech Detection","created":"2023-08-31","cited_by_count":2,"area":null},{"id":"2311.13892","title":"General Phrase Debiaser: Debiasing Masked Language Models at a Multi-Token Level","created":"2023-11-23","cited_by_count":2,"area":null},{"id":"2406.04146","title":"Towards Understanding Task-agnostic Debiasing Through the Lenses of Intrinsic Bias and Forgetfulness","created":"2024-06-06","cited_by_count":2,"area":null},{"id":"2406.06599","title":"Anna Karenina Strikes Again: Pre-Trained LLM Embeddings May Favor High-Performing Learners","created":"2024-06-06","cited_by_count":2,"area":null},{"id":"2412.03537","title":"Evaluating Gender Bias Transfer between Pre-trained and Prompt-Adapted Language Models","created":"2024-12-04","cited_by_count":2,"area":null},{"id":"2211.14639","title":"Gender Biases Unexpectedly Fluctuate in the Pre-training Stage of Masked Language Models","created":"2022-11-26","cited_by_count":1,"area":null},{"id":"2305.12829","title":"On Bias and Fairness in NLP: Investigating the Impact of Bias and Debiasing in Language Models on the Fairness of Toxicity Detection","created":"2023-05-22","cited_by_count":1,"area":null},{"id":"2311.08472","title":"Selecting Shots for Demographic Fairness in Few-Shot Learning with Large Language Models","created":"2023-11-14","cited_by_count":1,"area":null},{"id":"2311.09109","title":"Does Pre-trained Language Model Actually Infer Unseen Links in Knowledge Graph Completion?","created":"2023-11-15","cited_by_count":1,"area":null},{"id":"2402.11710","title":"A Note on Bias to Complete","created":"2024-02-18","cited_by_count":1,"area":null},{"id":"2506.01709","title":"Fairness Dynamics During Training","created":"2025-06-02","cited_by_count":1,"area":null},{"id":"2507.11216","title":"EsBBQ and CaBBQ: The Spanish and Catalan Bias Benchmarks for Question Answering","created":"2025-07-15","cited_by_count":1,"area":null},{"id":"2401.15499","title":"Semantic Properties of cosine based bias scores for word embeddings","created":"2024-01-27","cited_by_count":0,"area":null},{"id":"2510.07662","title":"Textual Entailment is not a Better Bias Metric than Token Probability","created":"2025-10-09","cited_by_count":0,"area":null},{"id":"2601.17764","title":"Cross-Lingual Probing and Community-Grounded Analysis of Gender Bias in Low-Resource Bengali","created":"2026-01-25","cited_by_count":0,"area":null},{"id":"2602.09590","title":"Context-Aware Counterfactual Data Augmentation for Gender Bias Mitigation in Language Models","created":"2026-02-10","cited_by_count":0,"area":null}],"next_cursor":null}