{"total":69,"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":"2210.09150","title":"Prompting GPT-3 To Be Reliable","created":"2022-10-17","cited_by_count":260,"area":null},{"id":"2305.08283","title":"From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Models","created":"2023-05-15","cited_by_count":260,"area":null},{"id":"2310.09219","title":"\"Kelly is a Warm Person, Joseph is a Role Model\": Gender Biases in LLM-Generated Reference Letters","created":"2023-10-13","cited_by_count":199,"area":null},{"id":"2205.09209","title":"\"I'm sorry to hear that\": Finding New Biases in Language Models with a Holistic Descriptor Dataset","created":"2022-05-18","cited_by_count":162,"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":"2404.00929","title":"A Survey on Multilingual Large Language Models: Corpora, Alignment, and Bias","created":"2024-04-01","cited_by_count":84,"area":null},{"id":"2205.12586","title":"Perturbation Augmentation for Fairer NLP","created":"2022-05-25","cited_by_count":52,"area":null},{"id":"2402.04105","title":"Measuring Implicit Bias in Explicitly Unbiased Large Language Models","created":"2024-02-06","cited_by_count":51,"area":null},{"id":"2210.02938","title":"Debiasing isn't enough! -- On the Effectiveness of Debiasing MLMs and their Social Biases in Downstream Tasks","created":"2022-10-06","cited_by_count":48,"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":"2206.11684","title":"Theory-Grounded Measurement of U.S. Social Stereotypes in English Language Models","created":"2022-06-23","cited_by_count":35,"area":null},{"id":"2408.03907","title":"Decoding Biases: Automated Methods and LLM Judges for Gender Bias Detection in Language Models","created":"2024-08-07","cited_by_count":33,"area":null},{"id":"2303.06167","title":"Overwriting Pretrained Bias with Finetuning Data","created":"2023-03-10","cited_by_count":32,"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":"2210.11471","title":"Choose Your Lenses: Flaws in Gender Bias Evaluation","created":"2022-10-20","cited_by_count":29,"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":"2306.08158","title":"Sociodemographic Bias in Language Models: A Survey and Forward Path","created":"2023-06-13","cited_by_count":28,"area":null},{"id":"2311.18580","title":"FFT: Towards Harmlessness Evaluation and Analysis for LLMs with Factuality, Fairness, Toxicity","created":"2023-11-30","cited_by_count":25,"area":null},{"id":"2410.12864","title":"Investigating Implicit Bias in Large Language Models: A Large-Scale Study of Over 50 LLMs","created":"2024-10-13","cited_by_count":25,"area":null},{"id":"2210.14552","title":"A Robust Bias Mitigation Procedure Based on the Stereotype Content Model","created":"2022-10-26","cited_by_count":24,"area":null},{"id":"2301.09211","title":"An Empirical Study of Metrics to Measure Representational Harms in Pre-Trained Language Models","created":"2023-01-22","cited_by_count":24,"area":null},{"id":"2406.11565","title":"Extrinsic Evaluation of Cultural Competence in Large Language Models","created":"2024-06-17","cited_by_count":24,"area":null},{"id":"2502.01926","title":"Fairness through Difference Awareness: Measuring Desired Group Discrimination in LLMs","created":"2025-02-04","cited_by_count":20,"area":null},{"id":"2302.12578","title":"Fairness in Language Models Beyond English: Gaps and Challenges","created":"2023-02-24","cited_by_count":16,"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":"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":"2410.00545","title":"What the Harm? Quantifying the Tangible Impact of Gender Bias in Machine Translation with a Human-centered Study","created":"2024-10-01","cited_by_count":15,"area":null},{"id":"2204.06827","title":"How Gender Debiasing Affects Internal Model Representations, and Why It Matters","created":"2022-04-14","cited_by_count":12,"area":null},{"id":"2307.04303","title":"Learning to Generate Equitable Text in Dialogue from Biased Training Data","created":"2023-07-10","cited_by_count":12,"area":null},{"id":"2312.00194","title":"Robust Concept Erasure via Kernelized Rate-Distortion Maximization","created":"2023-11-30","cited_by_count":11,"area":null},{"id":"2406.03953","title":"Tox-BART: Leveraging Toxicity Attributes for Explanation Generation of Implicit Hate Speech","created":"2024-06-06","cited_by_count":11,"area":null},{"id":"2305.12757","title":"This Prompt is Measuring <MASK>: Evaluating Bias Evaluation in Language Models","created":"2023-05-22","cited_by_count":9,"area":null},{"id":"2302.12640","title":"In-Depth Look at Word Filling Societal Bias Measures","created":"2023-02-24","cited_by_count":8,"area":null},{"id":"2310.08795","title":"Mitigating Bias for Question Answering Models by Tracking Bias Influence","created":"2023-10-13","cited_by_count":8,"area":null},{"id":"2504.17075","title":"Agree to Disagree? A Meta-Evaluation of LLM Misgendering","created":"2025-04-23","cited_by_count":7,"area":null},{"id":"2205.09867","title":"Gender Bias in Meta-Embeddings","created":"2022-05-19","cited_by_count":6,"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":"2406.11109","title":"Investigating Annotator Bias in Large Language Models for Hate Speech Detection","created":"2024-06-17","cited_by_count":6,"area":null},{"id":"2409.10825","title":"Unveiling and Mitigating Bias in Large Language Model Recommendations: A Path to Fairness","created":"2024-09-17","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":"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":"2211.13709","title":"Undesirable Biases in NLP: Addressing Challenges of Measurement","created":"2022-11-24","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":"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":"2601.18486","title":"Different Demographic Cues Yield Inconsistent Conclusions About LLM Personalization and Bias","created":"2026-01-26","cited_by_count":4,"area":null},{"id":"2501.01168","title":"Blind Men and the Elephant: Diverse Perspectives on Gender Stereotypes in Benchmark Datasets","created":"2025-01-02","cited_by_count":3,"area":null},{"id":"2506.04482","title":"Understanding and Meeting Practitioner Needs When Measuring Representational Harms Caused by LLM-Based Systems","created":"2025-06-04","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":"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":"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":"2409.20390","title":"When Stereotypes GTG: The Impact of Predictive Text Suggestions on Gender Bias in Human-AI Co-Writing","created":"2024-09-30","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":"2504.01369","title":"LITE: LLM-Impelled efficient Taxonomy Evaluation","created":"2025-04-02","cited_by_count":2,"area":null},{"id":"2510.24488","title":"A word association network methodology for evaluating implicit biases in LLMs compared to humans","created":"2025-10-28","cited_by_count":2,"area":null},{"id":"2210.10012","title":"Log-linear Guardedness and its Implications","created":"2022-10-18","cited_by_count":1,"area":null},{"id":"2212.07547","title":"Unsupervised Detection of Contextualized Embedding Bias with Application to Ideology","created":"2022-12-14","cited_by_count":1,"area":null},{"id":"2305.12620","title":"Keeping Up with the Language Models: Systematic Benchmark Extension for Bias Auditing","created":"2023-05-22","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":"2405.19299","title":"Expert-Guided Extinction of Toxic Tokens for Debiased Generation","created":"2024-05-29","cited_by_count":1,"area":null},{"id":"2409.09260","title":"Analyzing Correlations Between Intrinsic and Extrinsic Bias Metrics of Static Word Embeddings With Their Measuring Biases Aligned","created":"2024-09-14","cited_by_count":1,"area":null},{"id":"2410.19812","title":"Ethics Whitepaper: Whitepaper on Ethical Research into Large Language Models","created":"2024-10-17","cited_by_count":1,"area":null},{"id":"2501.04316","title":"Small Changes, Large Consequences: Analyzing the Allocational Fairness of LLMs in Hiring Contexts","created":"2025-01-08","cited_by_count":1,"area":null},{"id":"2503.06734","title":"Gender Encoding Patterns in Pretrained Language Model Representations","created":"2025-03-09","cited_by_count":1,"area":null},{"id":"2506.02321","title":"Quantifying Misattribution Unfairness in Authorship Attribution","created":"2025-06-02","cited_by_count":0,"area":null},{"id":"2601.09421","title":"Bias Dynamics in BabyLMs: Towards a Compute-Efficient Sandbox for Democratising Pre-Training Debiasing","created":"2026-01-14","cited_by_count":0,"area":null},{"id":"2608.11171","title":"From Interpretability to Control: Insights from Six Years of the TrustNLP Workshop","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2609.10060","title":"Reference-Based Bias Detection in LLMs via Relative Representations of Hidden States","created":"2026-09-09","cited_by_count":0,"area":null}],"next_cursor":null}