{"total":51,"rows":[{"id":"2110.08193","title":"BBQ: A Hand-Built Bias Benchmark for Question Answering","created":"2021-10-15","cited_by_count":701,"area":null},{"id":"2202.07206","title":"Impact of Pretraining Term Frequencies on Few-Shot Reasoning","created":"2022-02-15","cited_by_count":142,"area":"lr"},{"id":"2211.13972","title":"Picking on the Same Person: Does Algorithmic Monoculture lead to Outcome Homogenization?","created":"2022-11-25","cited_by_count":91,"area":null},{"id":"2103.01378","title":"Contrastive Explanations for Model Interpretability","created":"2021-03-02","cited_by_count":75,"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":"2205.02526","title":"Theories of \"Gender\" in NLP Bias Research","created":"2022-05-05","cited_by_count":62,"area":null},{"id":"2205.00551","title":"Gender Bias in Masked Language Models for Multiple Languages","created":"2022-05-01","cited_by_count":60,"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":"2101.11974","title":"Disembodied Machine Learning: On the Illusion of Objectivity in NLP","created":"2021-01-28","cited_by_count":37,"area":null},{"id":"2104.13640","title":"Societal Biases in Retrieved Contents: Measurement Framework and Adversarial Mitigation for BERT Rankers","created":"2021-04-28","cited_by_count":35,"area":null},{"id":"2302.10908","title":"Human-Centric Multimodal Machine Learning: Recent Advances and Testbed on AI-based Recruitment","created":"2023-02-13","cited_by_count":33,"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":"2305.10204","title":"Shielded Representations: Protecting Sensitive Attributes Through Iterative Gradient-Based Projection","created":"2023-05-17","cited_by_count":25,"area":null},{"id":"2109.03300","title":"Hi, my name is Martha: Using names to measure and mitigate bias in generative dialogue models","created":"2021-09-07","cited_by_count":23,"area":null},{"id":"2405.17159","title":"Stop! In the Name of Flaws: Disentangling Personal Names and Sociodemographic Attributes in NLP","created":"2024-05-27","cited_by_count":22,"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":"2407.12858","title":"Grounding and Evaluation for Large Language Models: Practical Challenges and Lessons Learned (Survey)","created":"2024-07-10","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":"2403.13213","title":"From Representational Harms to Quality-of-Service Harms: A Case Study on Llama 2 Safety Safeguards","created":"2024-03-20","cited_by_count":17,"area":null},{"id":"2202.11812","title":"Investigations of Performance and Bias in Human-AI Teamwork in Hiring","created":"2022-02-21","cited_by_count":16,"area":null},{"id":"2202.00035","title":"Learning Fair Representations via Rate-Distortion Maximization","created":"2022-01-31","cited_by_count":15,"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":"2103.16714","title":"Statistical inference for individual fairness","created":"2021-03-30","cited_by_count":13,"area":null},{"id":"2205.00504","title":"Domain Adaptation meets Individual Fairness. And they get along","created":"2022-05-01","cited_by_count":13,"area":null},{"id":"2311.07682","title":"Fuse to Forget: Bias Reduction and Selective Memorization through Model Fusion","created":"2023-11-13","cited_by_count":13,"area":null},{"id":"2404.01461","title":"Will the Real Linda Please Stand up...to Large Language Models? Examining the Representativeness Heuristic in LLMs","created":"2024-04-01","cited_by_count":13,"area":null},{"id":"2506.11880","title":"Addressing Bias in LLMs: Strategies and Application to Fair AI-based Recruitment","created":"2025-06-13","cited_by_count":13,"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":"2302.05711","title":"Fair Enough: Standardizing Evaluation and Model Selection for Fairness Research in NLP","created":"2023-02-11","cited_by_count":11,"area":null},{"id":"2310.15398","title":"\"One-Size-Fits-All\"? Examining Expectations around What Constitute \"Fair\" or \"Good\" NLG System Behaviors","created":"2023-10-23","cited_by_count":11,"area":null},{"id":"2205.06135","title":"Fair NLP Models with Differentially Private Text Encoders","created":"2022-05-12","cited_by_count":9,"area":null},{"id":"2401.16457","title":"Effective Controllable Bias Mitigation for Classification and Retrieval using Gate Adapters","created":"2024-01-29","cited_by_count":8,"area":null},{"id":"2403.06606","title":"Distributionally Generative Augmentation for Fair Facial Attribute Classification","created":"2024-03-11","cited_by_count":8,"area":null},{"id":"2108.11056","title":"Social Norm Bias: Residual Harms of Fairness-Aware Algorithms","created":"2021-08-25","cited_by_count":6,"area":null},{"id":"2111.04673","title":"Information-Theoretic Bias Assessment Of Learned Representations Of Pretrained Face Recognition","created":"2021-11-08","cited_by_count":5,"area":null},{"id":"2205.02414","title":"Subverting Fair Image Search with Generative Adversarial Perturbations","created":"2022-05-05","cited_by_count":5,"area":null},{"id":"2208.12212","title":"Sustaining Fairness via Incremental Learning","created":"2022-08-25","cited_by_count":5,"area":null},{"id":"2404.00463","title":"Addressing Both Statistical and Causal Gender Fairness in NLP Models","created":"2024-03-30","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":"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":"2111.07448","title":"Contrastive Clustering: Toward Unsupervised Bias Reduction for Emotion and Sentiment Classification","created":"2021-11-14","cited_by_count":1,"area":null},{"id":"2305.13833","title":"Reducing Sensitivity on Speaker Names for Text Generation from Dialogues","created":"2023-05-23","cited_by_count":1,"area":null},{"id":"2407.06917","title":"Who is better at math, Jenny or Jingzhen? Uncovering Stereotypes in Large Language Models","created":"2024-07-09","cited_by_count":1,"area":null},{"id":"2604.00011","title":"Quantifying Gender Bias in Large Language Models: When ChatGPT Becomes a Hiring Manager","created":"2026-03-10","cited_by_count":1,"area":null},{"id":"2305.12671","title":"Transferring Fairness using Multi-Task Learning with Limited Demographic Information","created":"2023-05-22","cited_by_count":0,"area":null},{"id":"2606.12088","title":"Debiasing Without Protected Attributes: Latent Concept Erasure from Textual Profiles","created":"2026-06-10","cited_by_count":0,"area":null},{"id":"2607.16620","title":"Privacy Cost as Equity Input: A Group Fairness Criterion for Differentially Private Machine Learning","created":"2026-07-18","cited_by_count":0,"area":"safety"},{"id":"2608.04268","title":"The Fairness Collapse Phenomenon: Bias Amplification in Language Models Trained on Synthetic Data","created":"2026-08-04","cited_by_count":0,"area":"synth"},{"id":"2608.21206","title":"No PUN Intended: Plausible Unknown Names for Person-Centred LLM Evaluation","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2609.30642","title":"A Framework for Identifying, Categorizing, and Explaining Bias in AI-Generated Code","created":"2026-09-25","cited_by_count":0,"area":null}],"next_cursor":null}