{"total":40,"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":"2306.03819","title":"LEACE: Perfect linear concept erasure in closed form","created":"2023-06-06","cited_by_count":267,"area":null},{"id":"2305.14456","title":"Having Beer after Prayer? Measuring Cultural Bias in Large Language Models","created":"2023-05-23","cited_by_count":153,"area":null},{"id":"2108.12084","title":"Harms of Gender Exclusivity and Challenges in Non-Binary Representation in Language Technologies","created":"2021-08-27","cited_by_count":128,"area":null},{"id":"2201.12091","title":"Linear Adversarial Concept Erasure","created":"2022-01-28","cited_by_count":101,"area":null},{"id":"2308.10149","title":"A Survey on Fairness in Large Language Models","created":"2023-08-20","cited_by_count":95,"area":null},{"id":"2108.03362","title":"On Measures of Biases and Harms in NLP","created":"2021-08-07","cited_by_count":81,"area":null},{"id":"2305.11840","title":"SeeGULL: A Stereotype Benchmark with Broad Geo-Cultural Coverage Leveraging Generative Models","created":"2023-05-19","cited_by_count":66,"area":null},{"id":"2401.05778","title":"Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems","created":"2024-01-11","cited_by_count":66,"area":null},{"id":"2306.03950","title":"MISGENDERED: Limits of Large Language Models in Understanding Pronouns","created":"2023-06-06","cited_by_count":43,"area":null},{"id":"2210.10040","title":"The Tail Wagging the Dog: Dataset Construction Biases of Social Bias Benchmarks","created":"2022-10-18","cited_by_count":31,"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":"2110.07871","title":"Socially Aware Bias Measurements for Hindi Language Representations","created":"2021-10-15","cited_by_count":29,"area":null},{"id":"2306.04597","title":"Language Models Get a Gender Makeover: Mitigating Gender Bias with Few-Shot Data Interventions","created":"2023-06-07","cited_by_count":28,"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":"2211.05617","title":"Debiasing Methods for Fairer Neural Models in Vision and Language Research: A Survey","created":"2022-11-10","cited_by_count":22,"area":null},{"id":"2307.01595","title":"Prompt Tuning Pushes Farther, Contrastive Learning Pulls Closer: A Two-Stage Approach to Mitigate Social Biases","created":"2023-07-04","cited_by_count":21,"area":null},{"id":"2309.08836","title":"Bias and Fairness in Chatbots: An Overview","created":"2023-09-16","cited_by_count":20,"area":null},{"id":"2212.04273","title":"Better Hit the Nail on the Head than Beat around the Bush: Removing Protected Attributes with a Single Projection","created":"2022-12-08","cited_by_count":17,"area":null},{"id":"2202.00035","title":"Learning Fair Representations via Rate-Distortion Maximization","created":"2022-01-31","cited_by_count":15,"area":null},{"id":"2402.15481","title":"Bias and Volatility: A Statistical Framework for Evaluating Large Language Model's Stereotypes and the Associated Generation Inconsistency","created":"2024-02-23","cited_by_count":15,"area":null},{"id":"2312.01509","title":"Tackling Bias in Pre-trained Language Models: Current Trends and Under-represented Societies","created":"2023-12-03","cited_by_count":11,"area":null},{"id":"2109.14039","title":"Marked Attribute Bias in Natural Language Inference","created":"2021-09-28","cited_by_count":6,"area":null},{"id":"2302.02997","title":"Erasure of Unaligned Attributes from Neural Representations","created":"2023-02-06","cited_by_count":6,"area":null},{"id":"2310.11991","title":"Removing Spurious Concepts from Neural Network Representations via Joint Subspace Estimation","created":"2023-10-18","cited_by_count":6,"area":null},{"id":"2503.20098","title":"Fundamental Limits of Perfect Concept Erasure","created":"2025-03-25","cited_by_count":6,"area":null},{"id":"2503.06792","title":"On the Mutual Influence of Gender and Occupation in LLM Representations","created":"2025-03-09","cited_by_count":4,"area":null},{"id":"2506.10703","title":"Preserving Task-Relevant Information Under Linear Concept Removal","created":"2025-06-12","cited_by_count":4,"area":null},{"id":"2104.02797","title":"VERB: Visualizing and Interpreting Bias Mitigation Techniques for Word Representations","created":"2021-04-06","cited_by_count":3,"area":null},{"id":"2311.17259","title":"SoUnD Framework: Analyzing (So)cial Representation in (Un)structured (D)ata","created":"2023-11-28","cited_by_count":3,"area":null},{"id":"2203.05140","title":"Speciesist Language and Nonhuman Animal Bias in English Masked Language Models","created":"2022-03-10","cited_by_count":2,"area":null},{"id":"2406.00787","title":"Applying Intrinsic Debiasing on Downstream Tasks: Challenges and Considerations for Machine Translation","created":"2024-06-02","cited_by_count":2,"area":null},{"id":"2209.13487","title":"Sentiment is all you need to win US Presidential elections","created":"2022-09-27","cited_by_count":1,"area":null},{"id":"2210.10012","title":"Log-linear Guardedness and its Implications","created":"2022-10-18","cited_by_count":1,"area":null},{"id":"2309.08624","title":"Challenges in Annotating Datasets to Quantify Bias in Under-represented Society","created":"2023-09-11","cited_by_count":1,"area":null},{"id":"2508.07516","title":"Augmenting Bias Detection in LLMs Using Topological Data Analysis","created":"2025-08-11","cited_by_count":1,"area":null},{"id":"2402.07519","title":"MAFIA: Multi-Adapter Fused Inclusive LanguAge Models","created":"2024-02-12","cited_by_count":0,"area":null},{"id":"2402.10899","title":"Taxonomy-based CheckList for Large Language Model Evaluation","created":"2023-12-15","cited_by_count":0,"area":null},{"id":"2506.22372","title":"Towards Fair Rankings: Leveraging LLMs for Gender Bias Detection and Measurement","created":"2025-06-27","cited_by_count":0,"area":null},{"id":"2606.30152","title":"Estimating Grammatical Gender Directions in Contextual Embeddings under Controlled and Natural Contexts","created":"2026-06-29","cited_by_count":0,"area":null}],"next_cursor":null}