{"total":100,"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":"2302.03494","title":"A Categorical Archive of ChatGPT Failures","created":"2023-02-06","cited_by_count":168,"area":null},{"id":"2110.08527","title":"An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained Language Models","created":"2021-10-16","cited_by_count":97,"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":"2302.11529","title":"Modular Deep Learning","created":"2023-02-22","cited_by_count":83,"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":"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":"2210.07626","title":"BERTScore is Unfair: On Social Bias in Language Model-Based Metrics for Text Generation","created":"2022-10-14","cited_by_count":48,"area":null},{"id":"2202.11923","title":"Welcome to the Modern World of Pronouns: Identity-Inclusive Natural Language Processing beyond Gender","created":"2022-02-24","cited_by_count":47,"area":null},{"id":"2406.16678","title":"Segment Any Text: A Universal Approach for Robust, Efficient and Adaptable Sentence Segmentation","created":"2024-06-24","cited_by_count":41,"area":null},{"id":"2210.14169","title":"Weakly Supervised Data Augmentation Through Prompting for Dialogue Understanding","created":"2022-10-25","cited_by_count":32,"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":"2307.01503","title":"On Evaluating and Mitigating Gender Biases in Multilingual Settings","created":"2023-07-04","cited_by_count":31,"area":null},{"id":"2205.10400","title":"Multi2WOZ: A Robust Multilingual Dataset and Conversational Pretraining for Task-Oriented Dialog","created":"2022-05-20","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":"2304.10153","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":"2409.08087","title":"Securing Large Language Models: Addressing Bias, Misinformation, and Prompt Attacks","created":"2024-09-12","cited_by_count":26,"area":"safety"},{"id":"2302.06321","title":"Parameter-efficient Modularised Bias Mitigation via AdapterFusion","created":"2023-02-13","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":"2402.06900","title":"Can LLMs Recognize Toxicity? A Structured Investigation Framework and Toxicity Metric","created":"2024-02-10","cited_by_count":23,"area":null},{"id":"2403.09193","title":"Can We Talk Models Into Seeing the World Differently?","created":"2024-03-14","cited_by_count":23,"area":"mllm"},{"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":"2406.08824","title":"LLM-Driven Robots Risk Enacting Discrimination, Violence, and Unlawful Actions","created":"2024-06-13","cited_by_count":22,"area":null},{"id":"2110.08395","title":"DS-TOD: Efficient Domain Specialization for Task Oriented Dialog","created":"2021-10-15","cited_by_count":21,"area":null},{"id":"2403.08743","title":"Prompting Fairness: Integrating Causality to Debias Large Language Models","created":"2024-03-13","cited_by_count":21,"area":null},{"id":"2112.07447","title":"Measuring Fairness with Biased Rulers: A Survey on Quantifying Biases in Pretrained Language Models","created":"2021-12-14","cited_by_count":20,"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":"2204.04026","title":"Fair and Argumentative Language Modeling for Computational Argumentation","created":"2022-04-08","cited_by_count":18,"area":null},{"id":"2205.15171","title":"Modular and On-demand Bias Mitigation with Attribute-Removal Subnetworks","created":"2022-05-30","cited_by_count":18,"area":null},{"id":"2405.06346","title":"Akal Badi ya Bias: An Exploratory Study of Gender Bias in Hindi Language Technology","created":"2024-05-10","cited_by_count":17,"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":"2306.04067","title":"An Empirical Analysis of Parameter-Efficient Methods for Debiasing Pre-Trained Language Models","created":"2023-06-06","cited_by_count":16,"area":null},{"id":"2405.09341","title":"Large Language Model Bias Mitigation from the Perspective of Knowledge Editing","created":"2024-05-15","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":"2407.04434","title":"From 'Showgirls' to 'Performers': Fine-tuning with Gender-inclusive Language for Bias Reduction in LLMs","created":"2024-07-05","cited_by_count":15,"area":null},{"id":"2208.08176","title":"Visual Comparison of Language Model Adaptation","created":"2022-08-17","cited_by_count":14,"area":null},{"id":"2310.10310","title":"Investigating Bias in Multilingual Language Models: Cross-Lingual Transfer of Debiasing Techniques","created":"2023-10-16","cited_by_count":14,"area":null},{"id":"2311.10395","title":"Bias A-head? Analyzing Bias in Transformer-Based Language Model Attention Heads","created":"2023-11-17","cited_by_count":14,"area":null},{"id":"2501.14457","title":"Understanding and Mitigating Gender Bias in LLMs via Interpretable Neuron Editing","created":"2025-01-24","cited_by_count":14,"area":null},{"id":"2408.11843","title":"Identifying and Mitigating Social Bias Knowledge in Language Models","created":"2024-08-07","cited_by_count":13,"area":null},{"id":"2302.13136","title":"Toward Fairness in Text Generation via Mutual Information Minimization based on Importance Sampling","created":"2023-02-25","cited_by_count":12,"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":"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":"2402.13636","title":"A Unified Framework and Dataset for Assessing Societal Bias in Vision-Language Models","created":"2024-02-21","cited_by_count":11,"area":"mllm"},{"id":"2407.18454","title":"Fairness Definitions in Language Models Explained","created":"2024-07-26","cited_by_count":11,"area":null},{"id":"2210.07362","title":"Can Demographic Factors Improve Text Classification? Revisiting Demographic Adaptation in the Age of Transformers","created":"2022-10-13","cited_by_count":10,"area":null},{"id":"2305.14016","title":"Target-Agnostic Gender-Aware Contrastive Learning for Mitigating Bias in Multilingual Machine Translation","created":"2023-05-23","cited_by_count":10,"area":null},{"id":"2205.10828","title":"What Do Compressed Multilingual Machine Translation Models Forget?","created":"2022-05-22","cited_by_count":9,"area":null},{"id":"2207.04546","title":"FairDistillation: Mitigating Stereotyping in Language Models","created":"2022-07-10","cited_by_count":8,"area":null},{"id":"2308.01948","title":"A Multidimensional Analysis of Social Biases in Vision Transformers","created":"2023-08-03","cited_by_count":8,"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":"2211.04281","title":"SocioProbe: What, When, and Where Language Models Learn about Sociodemographics","created":"2022-11-08","cited_by_count":7,"area":null},{"id":"2305.14307","title":"Debiasing should be Good and Bad: Measuring the Consistency of Debiasing Techniques in Language Models","created":"2023-05-23","cited_by_count":7,"area":null},{"id":"2408.00992","title":"Fairness in Large Language Models in Three Hours","created":"2024-08-02","cited_by_count":7,"area":null},{"id":"2511.18635","title":"No Free Lunch in Language Model Bias Mitigation? Targeted Bias Reduction Can Exacerbate Unmitigated LLM Biases","created":"2025-11-23","cited_by_count":7,"area":null},{"id":"2305.17660","title":"Plug-and-Play Document Modules for Pre-trained Models","created":"2023-05-28","cited_by_count":6,"area":null},{"id":"2305.17691","title":"Plug-and-Play Knowledge Injection for Pre-trained Language Models","created":"2023-05-28","cited_by_count":6,"area":null},{"id":"2211.04256","title":"Bridging Fairness and Environmental Sustainability in Natural Language Processing","created":"2022-11-08","cited_by_count":5,"area":null},{"id":"2403.07627","title":"generAItor: Tree-in-the-Loop Text Generation for Language Model Explainability and Adaptation","created":"2024-03-12","cited_by_count":5,"area":null},{"id":"2405.06687","title":"Hire Me or Not? Examining Language Model's Behavior with Occupation Attributes","created":"2024-05-06","cited_by_count":5,"area":null},{"id":"2406.12800","title":"Supporting Human Raters with the Detection of Harmful Content using Large Language Models","created":"2024-06-18","cited_by_count":5,"area":"safety"},{"id":"2412.14050","title":"Cross-Lingual Transfer of Debiasing and Detoxification in Multilingual LLMs: An Extensive Investigation","created":"2024-12-18","cited_by_count":5,"area":null},{"id":"2503.15815","title":"Attention Pruning: Automated Fairness Repair of Language Models via Surrogate Simulated Annealing","created":"2025-03-20","cited_by_count":5,"area":null},{"id":"2305.14936","title":"Trade-Offs Between Fairness and Privacy in Language Modeling","created":"2023-05-24","cited_by_count":4,"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":"2312.15478","title":"A Group Fairness Lens for Large Language Models","created":"2023-12-24","cited_by_count":4,"area":null},{"id":"2401.12756","title":"What the Weight?! A Unified Framework for Zero-Shot Knowledge Composition","created":"2024-01-23","cited_by_count":4,"area":null},{"id":"2510.06354","title":"LLM Bias Detection and Mitigation through the Lens of Desired Distributions","created":"2025-10-07","cited_by_count":4,"area":null},{"id":"2210.06245","title":"Back to the Future: On Potential Histories in NLP","created":"2022-10-12","cited_by_count":3,"area":null},{"id":"2407.11203","title":"The Life Cycle of Large Language Models: A Review of Biases in Education","created":"2024-06-03","cited_by_count":3,"area":null},{"id":"2410.17739","title":"Local Contrastive Editing of Gender Stereotypes","created":"2024-10-23","cited_by_count":3,"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":"2502.07017","title":"Finding Words Associated with DIF: Predicting Differential Item Functioning using LLMs and Explainable AI","created":"2025-02-10","cited_by_count":3,"area":null},{"id":"2112.08637","title":"Analyzing the Limits of Self-Supervision in Handling Bias in Language","created":"2021-12-16","cited_by_count":2,"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":"2208.10734","title":"Learning Dynamic Contextualised Word Embeddings via Template-based Temporal Adaptation","created":"2022-08-23","cited_by_count":2,"area":null},{"id":"2310.01217","title":"ScaLearn: Simple and Highly Parameter-Efficient Task Transfer by Learning to Scale","created":"2023-10-02","cited_by_count":2,"area":null},{"id":"2312.00434","title":"PEFTDebias : Capturing debiasing information using PEFTs","created":"2023-12-01","cited_by_count":2,"area":null},{"id":"2404.01253","title":"UniArk: Improving Generalisation and Consistency for Factual Knowledge Extraction through Debiasing","created":"2024-04-01","cited_by_count":2,"area":null},{"id":"2405.02010","title":"The Trade-off between Performance, Efficiency, and Fairness in Adapter Modules for Text Classification","created":"2024-05-03","cited_by_count":2,"area":null},{"id":"2505.15475","title":"LFTF: Locating First and Then Fine-Tuning for Mitigating Gender Bias in Large Language Models","created":"2025-05-21","cited_by_count":2,"area":null},{"id":"2507.02595","title":"MPF: Aligning and Debiasing Language Models post Deployment via Multi Perspective Fusion","created":"2025-07-03","cited_by_count":2,"area":null},{"id":"2509.24468","title":"Bias Mitigation or Cultural Commonsense? Evaluating LLMs with a Japanese Dataset","created":"2025-09-29","cited_by_count":2,"area":null},{"id":"2306.08010","title":"Domain Information Control at Inference Time for Acoustic Scene Classification","created":"2023-06-13","cited_by_count":1,"area":null},{"id":"2310.15724","title":"Variator: Accelerating Pre-trained Models with Plug-and-Play Compression Modules","created":"2023-10-24","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":"2410.05349","title":"SoK: Towards Security and Safety of Edge AI","created":"2024-10-07","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":"2506.11244","title":"Iterative Multilingual Spectral Attribute Erasure","created":"2025-06-12","cited_by_count":1,"area":null},{"id":"2512.04691","title":"Towards Ethical Multi-Agent Systems of Large Language Models: A Mechanistic Interpretability Perspective","created":"2025-12-04","cited_by_count":1,"area":"agents"},{"id":"2208.01018","title":"Massively Multilingual Lexical Specialization of Multilingual Transformers","created":"2022-08-01","cited_by_count":0,"area":null},{"id":"2402.07519","title":"MAFIA: Multi-Adapter Fused Inclusive LanguAge Models","created":"2024-02-12","cited_by_count":0,"area":null},{"id":"2406.04876","title":"HateDebias: On the Diversity and Variability of Hate Speech Debiasing","created":"2024-06-07","cited_by_count":0,"area":null},{"id":"2508.03677","title":"FairLangProc: A Python package for fairness in NLP","created":"2025-08-05","cited_by_count":0,"area":null},{"id":"2509.23805","title":"Open-DeBias: Toward Mitigating Open-Set Bias in Language Models","created":"2025-09-28","cited_by_count":0,"area":null},{"id":"2512.03082","title":"Alleviating Choice Supportive Bias in LLM with Reasoning Dependency Generation","created":"2025-11-28","cited_by_count":0,"area":"lr"},{"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":"2604.16780","title":"FairNVT: Fair Classification via Noise Injection in Vision Transformers","created":"2026-04-18","cited_by_count":0,"area":null}],"next_cursor":null}