{"total":211,"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":"2309.00770","title":"Bias and Fairness in Large Language Models: A Survey","created":"2023-09-02","cited_by_count":639,"area":null},{"id":"2105.03075","title":"A Survey of Data Augmentation Approaches for NLP","created":"2021-05-07","cited_by_count":409,"area":null},{"id":"2101.05783","title":"Persistent Anti-Muslim Bias in Large Language Models","created":"2021-01-14","cited_by_count":377,"area":null},{"id":"2105.04054","title":"Societal Biases in Language Generation: Progress and Challenges","created":"2021-05-10","cited_by_count":202,"area":null},{"id":"2308.14921","title":"Gender bias and stereotypes in Large Language Models","created":"2023-08-28","cited_by_count":187,"area":null},{"id":"2103.14659","title":"Alignment of Language Agents","created":"2021-03-26","cited_by_count":168,"area":null},{"id":"2104.06001","title":"Gender Bias in Machine Translation","created":"2021-04-13","cited_by_count":117,"area":null},{"id":"2110.12884","title":"DECAF: Generating Fair Synthetic Data Using Causally-Aware Generative Networks","created":"2021-10-25","cited_by_count":109,"area":null},{"id":"2203.07785","title":"The Ghost in the Machine has an American accent: value conflict in GPT-3","created":"2022-03-15","cited_by_count":105,"area":null},{"id":"2109.03646","title":"Sustainable Modular Debiasing of Language Models","created":"2021-09-08","cited_by_count":100,"area":null},{"id":"2404.11457","title":"Bias and Unfairness in Information Retrieval Systems: New Challenges in the LLM Era","created":"2024-04-17","cited_by_count":98,"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":"2107.06641","title":"Trustworthy AI: A Computational Perspective","created":"2021-07-12","cited_by_count":93,"area":null},{"id":"2112.14168","title":"A Survey on Gender Bias in Natural Language Processing","created":"2021-12-28","cited_by_count":89,"area":null},{"id":"2109.05704","title":"Mitigating Language-Dependent Ethnic Bias in BERT","created":"2021-09-13","cited_by_count":87,"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":"2503.16527","title":"LLM Generated Persona is a Promise with a Catch","created":"2025-03-18","cited_by_count":81,"area":null},{"id":"2301.07573","title":"Synthcity: facilitating innovative use cases of synthetic data in different data modalities","created":"2023-01-18","cited_by_count":76,"area":null},{"id":"2112.02721","title":"NL-Augmenter: A Framework for Task-Sensitive Natural Language Augmentation","created":"2021-12-06","cited_by_count":73,"area":null},{"id":"2205.03257","title":"Synthetic Data -- what, why and how?","created":"2022-05-06","cited_by_count":67,"area":null},{"id":"2403.19827","title":"Language Models Learn Rare Phenomena from Less Rare Phenomena: The Case of the Missing AANNs","created":"2024-03-28","cited_by_count":65,"area":null},{"id":"2205.02526","title":"Theories of \"Gender\" in NLP Bias Research","created":"2022-05-05","cited_by_count":62,"area":null},{"id":"2402.01981","title":"Self-Debiasing Large Language Models: Zero-Shot Recognition and Reduction of Stereotypes","created":"2024-02-03","cited_by_count":59,"area":null},{"id":"2306.11507","title":"TrustGPT: A Benchmark for Trustworthy and Responsible Large Language Models","created":"2023-06-20","cited_by_count":58,"area":null},{"id":"2404.01349","title":"Fairness in Large Language Models: A Taxonomic Survey","created":"2024-03-31","cited_by_count":58,"area":null},{"id":"2101.09688","title":"Stereotype and Skew: Quantifying Gender Bias in Pre-trained and Fine-tuned Language Models","created":"2021-01-24","cited_by_count":57,"area":null},{"id":"2106.12387","title":"Fairness in Cardiac MR Image Analysis: An Investigation of Bias Due to Data Imbalance in Deep Learning Based Segmentation","created":"2021-06-23","cited_by_count":57,"area":null},{"id":"2102.12594","title":"Directional Bias Amplification","created":"2021-02-24","cited_by_count":54,"area":null},{"id":"2311.16153","title":"Identifying and Mitigating Vulnerabilities in LLM-Integrated Applications","created":"2023-11-07","cited_by_count":54,"area":null},{"id":"2410.02584","title":"Towards Implicit Bias Detection and Mitigation in Multi-Agent LLM Interactions","created":"2024-10-03","cited_by_count":51,"area":"agents"},{"id":"2108.08504","title":"Understanding and Mitigating Annotation Bias in Facial Expression Recognition","created":"2021-08-19","cited_by_count":50,"area":null},{"id":"2109.06105","title":"NeuTral Rewriter: A Rule-Based and Neural Approach to Automatic Rewriting into Gender-Neutral Alternatives","created":"2021-09-13","cited_by_count":46,"area":null},{"id":"2107.00753","title":"An Investigation of the (In)effectiveness of Counterfactually Augmented Data","created":"2021-07-01","cited_by_count":42,"area":null},{"id":"2203.12574","title":"Mitigating Gender Bias in Distilled Language Models via Counterfactual Role Reversal","created":"2022-03-23","cited_by_count":40,"area":"distill"},{"id":"2504.14492","title":"FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering","created":"2025-04-20","cited_by_count":40,"area":"mechinterp"},{"id":"2109.08253","title":"Balancing out Bias: Achieving Fairness Through Balanced Training","created":"2021-09-16","cited_by_count":34,"area":null},{"id":"2112.06837","title":"Sparse Interventions in Language Models with Differentiable Masking","created":"2021-12-13","cited_by_count":34,"area":null},{"id":"2305.10510","title":"ChatGPT Perpetuates Gender Bias in Machine Translation and Ignores Non-Gendered Pronouns: Findings across Bengali and Five other Low-Resource Languages","created":"2023-05-17","cited_by_count":34,"area":null},{"id":"2104.08728","title":"Revealing Persona Biases in Dialogue Systems","created":"2021-04-18","cited_by_count":33,"area":null},{"id":"2210.04492","title":"Unified Detoxifying and Debiasing in Language Generation via Inference-time Adaptive Optimization","created":"2022-10-10","cited_by_count":33,"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":"2111.05204","title":"Reason first, then respond: Modular Generation for Knowledge-infused Dialogue","created":"2021-11-09","cited_by_count":32,"area":null},{"id":"2106.01127","title":"Towards Robust Classification Model by Counterfactual and Invariant Data Generation","created":"2021-06-02","cited_by_count":30,"area":null},{"id":"2106.15231","title":"Exploring the Efficacy of Automatically Generated Counterfactuals for Sentiment Analysis","created":"2021-06-29","cited_by_count":30,"area":null},{"id":"2110.00521","title":"Unpacking the Interdependent Systems of Discrimination: Ableist Bias in NLP Systems through an Intersectional Lens","created":"2021-10-01","cited_by_count":30,"area":null},{"id":"2501.17420","title":"Actions Speak Louder than Words: Agent Decisions Reveal Implicit Biases in Language Models","created":"2025-01-29","cited_by_count":30,"area":"agents"},{"id":"2304.03722","title":"Beyond Privacy: Navigating the Opportunities and Challenges of Synthetic Data","created":"2023-04-07","cited_by_count":29,"area":null},{"id":"2305.11262","title":"CHBias: Bias Evaluation and Mitigation of Chinese Conversational Language Models","created":"2023-05-18","cited_by_count":28,"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":"2304.03728","title":"Interpretable Unified Language Checking","created":"2023-04-07","cited_by_count":26,"area":null},{"id":"2309.14381","title":"Survey of Social Bias in Vision-Language Models","created":"2023-09-24","cited_by_count":26,"area":"mllm"},{"id":"2101.00411","title":"Substructure Substitution: Structured Data Augmentation for NLP","created":"2021-01-02","cited_by_count":25,"area":null},{"id":"2305.04990","title":"Explanation-based Finetuning Makes Models More Robust to Spurious Cues","created":"2023-05-08","cited_by_count":25,"area":null},{"id":"2310.18913","title":"Debiasing Algorithm through Model Adaptation","created":"2023-10-29","cited_by_count":24,"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":"2109.11708","title":"Detect and Perturb: Neutral Rewriting of Biased and Sensitive Text via Gradient-based Decoding","created":"2021-09-24","cited_by_count":23,"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":"2310.12611","title":"Identifying and Adapting Transformer-Components Responsible for Gender Bias in an English Language Model","created":"2023-10-19","cited_by_count":22,"area":null},{"id":"2204.04487","title":"Informativeness and Invariance: Two Perspectives on Spurious Correlations in Natural Language","created":"2022-04-09","cited_by_count":21,"area":null},{"id":"2205.11374","title":"Looking for a Handsome Carpenter! Debiasing GPT-3 Job Advertisements","created":"2022-05-23","cited_by_count":21,"area":null},{"id":"2207.02463","title":"Gender Biases and Where to Find Them: Exploring Gender Bias in Pre-Trained Transformer-based Language Models Using Movement Pruning","created":"2022-07-06","cited_by_count":21,"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":"2306.15298","title":"Gender Bias in BERT -- Measuring and Analysing Biases through Sentiment Rating in a Realistic Downstream Classification Task","created":"2023-06-27","cited_by_count":21,"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":"2406.19097","title":"Fairness and Bias in Multimodal AI: A Survey","created":"2024-06-27","cited_by_count":20,"area":"mllm"},{"id":"2205.06303","title":"Using Natural Sentences for Understanding Biases in Language Models","created":"2022-05-12","cited_by_count":19,"area":null},{"id":"2301.00395","title":"CORGI-PM: A Chinese Corpus For Gender Bias Probing and Mitigation","created":"2023-01-01","cited_by_count":19,"area":null},{"id":"2210.07455","title":"Controlling Bias Exposure for Fair Interpretable Predictions","created":"2022-10-14","cited_by_count":18,"area":null},{"id":"2503.08588","title":"BiasEdit: Debiasing Stereotyped Language Models via Model Editing","created":"2025-03-11","cited_by_count":18,"area":null},{"id":"2407.15366","title":"Walking in Others' Shoes: How Perspective-Taking Guides Large Language Models in Reducing Toxicity and Bias","created":"2024-07-22","cited_by_count":17,"area":null},{"id":"2206.12131","title":"MVP: Multi-task Supervised Pre-training for Natural Language Generation","created":"2022-06-24","cited_by_count":16,"area":null},{"id":"2207.10245","title":"The Birth of Bias: A case study on the evolution of gender bias in an English language model","created":"2022-07-21","cited_by_count":16,"area":null},{"id":"2110.08413","title":"Invariant Language Modeling","created":"2021-10-16","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":"2311.03311","title":"Unraveling Downstream Gender Bias from Large Language Models: A Study on AI Educational Writing Assistance","created":"2023-11-06","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":"2302.06975","title":"A Review of the Role of Causality in Developing Trustworthy AI Systems","created":"2023-02-14","cited_by_count":14,"area":null},{"id":"2306.14518","title":"Toward Fairness Through Fair Multi-Exit Framework for Dermatological Disease Diagnosis","created":"2023-06-26","cited_by_count":14,"area":null},{"id":"2311.18147","title":"DisCGen: A Framework for Discourse-Informed Counterspeech Generation","created":"2023-11-29","cited_by_count":14,"area":null},{"id":"2405.02225","title":"Fair Risk Control: A Generalized Framework for Calibrating Multi-group Fairness Risks","created":"2024-05-03","cited_by_count":14,"area":null},{"id":"2212.09006","title":"A Review of Speech-centric Trustworthy Machine Learning: Privacy, Safety, and Fairness","created":"2022-12-18","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":"2110.09216","title":"The Arabic Parallel Gender Corpus 2.0: Extensions and Analyses","created":"2021-10-18","cited_by_count":12,"area":null},{"id":"2305.17013","title":"D-CALM: A Dynamic Clustering-based Active Learning Approach for Mitigating Bias","created":"2023-05-26","cited_by_count":12,"area":null},{"id":"2310.09624","title":"ASSERT: Automated Safety Scenario Red Teaming for Evaluating the Robustness of Large Language Models","created":"2023-10-14","cited_by_count":12,"area":"safety"},{"id":"2101.02647","title":"From Learning to Relearning: A Framework for Diminishing Bias in Social Robot Navigation","created":"2021-01-07","cited_by_count":11,"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":"2211.03374","title":"Deep Causal Learning: Representation, Discovery and Inference","created":"2022-11-07","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":"2201.05177","title":"Making a (Counterfactual) Difference One Rationale at a Time","created":"2022-01-13","cited_by_count":10,"area":null},{"id":"2301.12855","title":"How Far Can It Go?: On Intrinsic Gender Bias Mitigation for Text Classification","created":"2023-01-30","cited_by_count":10,"area":null},{"id":"2401.08066","title":"Achieve Fairness without Demographics for Dermatological Disease Diagnosis","created":"2024-01-16","cited_by_count":10,"area":null},{"id":"2410.11114","title":"Active Learning for Robust and Representative LLM Generation in Safety-Critical Scenarios","created":"2024-10-14","cited_by_count":10,"area":null},{"id":"2203.17090","title":"PanGu-Bot: Efficient Generative Dialogue Pre-training from Pre-trained Language Model","created":"2022-03-31","cited_by_count":9,"area":null},{"id":"2310.17551","title":"Unpacking the Ethical Value Alignment in Big Models","created":"2023-10-26","cited_by_count":9,"area":null},{"id":"2410.07589","title":"No Free Lunch: Retrieval-Augmented Generation Undermines Fairness in LLMs, Even for Vigilant Users","created":"2024-10-10","cited_by_count":9,"area":"rag"},{"id":"2110.15733","title":"Detecting Gender Bias in Transformer-based Models: A Case Study on BERT","created":"2021-10-15","cited_by_count":8,"area":null},{"id":"2203.10675","title":"Mitigating Gender Bias in Machine Translation through Adversarial Learning","created":"2022-03-20","cited_by_count":8,"area":null}],"next_cursor":"100"}