{"total":59,"rows":[{"id":"2404.02062","title":"Digital Forgetting in Large Language Models: A Survey of Unlearning Methods","created":"2024-04-02","cited_by_count":40,"area":"safety"},{"id":"2407.03129","title":"Social Bias Evaluation for Large Language Models Requires Prompt Variations","created":"2024-07-03","cited_by_count":40,"area":null},{"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":"2404.17218","title":"Prompting Techniques for Reducing Social Bias in LLMs through System 1 and System 2 Cognitive Processes","created":"2024-04-26","cited_by_count":39,"area":null},{"id":"2406.07243","title":"MBBQ: A Dataset for Cross-Lingual Comparison of Stereotypes in Generative LLMs","created":"2024-06-11","cited_by_count":35,"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":"2407.13928","title":"BiasDPO: Mitigating Bias in Language Models through Direct Preference Optimization","created":"2024-07-18","cited_by_count":18,"area":"alignment"},{"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":"2504.16420","title":"A Survey of Foundation Model-Powered Recommender Systems: From Feature-Based, Generative to Agentic Paradigms","created":"2025-04-23","cited_by_count":17,"area":"agents"},{"id":"2506.05166","title":"Dissecting Bias in LLMs: A Mechanistic Interpretability Perspective","created":"2025-06-05","cited_by_count":15,"area":"mechinterp"},{"id":"2407.03536","title":"Social Bias in Large Language Models For Bangla: An Empirical Study on Gender and Religious Bias","created":"2024-07-03","cited_by_count":13,"area":null},{"id":"2412.06134","title":"Evaluating and Mitigating Social Bias for Large Language Models in Open-ended Settings","created":"2024-12-09","cited_by_count":10,"area":null},{"id":"2603.21524","title":"CatRAG: Functor-Guided Structural Debiasing with Retrieval Augmentation for Fair LLMs","created":"2026-03-23","cited_by_count":9,"area":null},{"id":"2412.15504","title":"Mitigating Social Bias in Large Language Models: A Multi-Objective Approach within a Multi-Agent Framework","created":"2024-12-20","cited_by_count":8,"area":"agents"},{"id":"2502.19749","title":"What's Not Said Still Hurts: A Description-Based Evaluation Framework for Measuring Social Bias in LLMs","created":"2025-02-27","cited_by_count":8,"area":null},{"id":"2512.23461","title":"Eliminating Inductive Bias in Reward Models with Information-Theoretic Guidance","created":"2025-12-29","cited_by_count":7,"area":"alignment"},{"id":"2503.00333","title":"More of the Same: Persistent Representational Harms Under Increased Representation","created":"2025-03-01","cited_by_count":6,"area":null},{"id":"2505.23829","title":"BiasFilter: An Inference-Time Debiasing Framework for Large Language Models","created":"2025-05-28","cited_by_count":6,"area":null},{"id":"2407.06432","title":"An Empirical Study of Gendered Stereotypes in Emotional Attributes for Bangla in Multilingual Large Language Models","created":"2024-07-08","cited_by_count":5,"area":null},{"id":"2408.11247","title":"Unboxing Occupational Bias: Grounded Debiasing of LLMs with U.S. Labor Data","created":"2024-08-20","cited_by_count":5,"area":null},{"id":"2512.23430","title":"C2PO: Diagnosing and Disentangling Bias Shortcuts in LLMs","created":"2025-12-29","cited_by_count":5,"area":null},{"id":"2602.04398","title":"Bi-directional Bias Attribution: Debiasing Large Language Models without Modifying Prompts","created":"2026-02-04","cited_by_count":5,"area":null},{"id":"2503.09219","title":"Rethinking Prompt-based Debiasing in Large Language Models","created":"2025-03-12","cited_by_count":4,"area":"lr"},{"id":"2504.21299","title":"BiasGuard: A Reasoning-enhanced Bias Detection Tool For Large Language Models","created":"2025-04-30","cited_by_count":4,"area":"lr"},{"id":"2411.17338","title":"Different Bias Under Different Criteria: Assessing Bias in LLMs with a Fact-Based Approach","created":"2024-11-26","cited_by_count":3,"area":null},{"id":"2507.00985","title":"Discourse Heuristics For Paradoxically Moral Self-Correction","created":"2025-07-01","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":"2601.14553","title":"Self-Blinding and Counterfactual Self-Simulation Mitigate Biases and Sycophancy in Large Language Models","created":"2026-01-21","cited_by_count":3,"area":null},{"id":"2604.08243","title":"Self-Debias: Self-correcting for Debiasing Large Language Models","created":"2026-04-09","cited_by_count":3,"area":"lr"},{"id":"2408.09489","title":"REFINE-LM: Mitigating Language Model Stereotypes via Reinforcement Learning","created":"2024-08-18","cited_by_count":2,"area":null},{"id":"2505.18466","title":"Purdah and Patriarchy: Evaluating and Mitigating South Asian Biases in Open-Ended Multilingual LLM Generations","created":"2025-05-24","cited_by_count":2,"area":null},{"id":"2507.05686","title":"Smoothie-Qwen: Post-Hoc Smoothing to Reduce Language Bias in Multilingual LLMs","created":"2025-07-08","cited_by_count":2,"area":null},{"id":"2509.02133","title":"AMBEDKAR-A Multi-level Bias Elimination through a Decoding Approach with Knowledge Augmentation for Robust Constitutional Alignment of Language Models","created":"2025-09-02","cited_by_count":2,"area":"alignment"},{"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":"2510.00232","title":"BiasFreeBench: a Benchmark for Mitigating Bias in Large Language Model Responses","created":"2025-09-30","cited_by_count":2,"area":null},{"id":"2511.00177","title":"Can SAEs reveal and mitigate racial biases of LLMs in healthcare?","created":"2025-10-31","cited_by_count":2,"area":"mechinterp"},{"id":"2511.02194","title":"Personalized Decision Modeling: Utility Optimization or Textualized-Symbolic Reasoning","created":"2025-11-04","cited_by_count":2,"area":"lr"},{"id":"2602.13253","title":"Implicit Bias in LLMs for Transgender Populations","created":"2026-02-02","cited_by_count":2,"area":null},{"id":"2403.14562","title":"Agentic AI: The Era of Semantic Decoding","created":"2024-03-21","cited_by_count":1,"area":"agents"},{"id":"2506.08487","title":"Beyond Bias Scores: Unmasking Vacuous Neutrality in Small Language Models","created":"2025-06-10","cited_by_count":1,"area":null},{"id":"2508.08855","title":"BiasGym: A Simple and Generalizable Framework for Analyzing and Removing Biases through Injection","created":"2025-08-12","cited_by_count":1,"area":null},{"id":"2509.04515","title":"Mitigation of Gender and Ethnicity Bias in AI-Generated Stories through Model Explanations","created":"2025-09-03","cited_by_count":1,"area":null},{"id":"2509.16462","title":"Let's Unlearn Stereotypes Before Decision-Making: Assessing the Impact of Intrinsic Bias Mitigation on Downstream Fairness in LLMs","created":"2025-09-19","cited_by_count":1,"area":"safety"},{"id":"2510.08145","title":"Mitigating Judgment Preference Bias in Large Language Models through Group-Based Polling","created":"2025-10-09","cited_by_count":1,"area":null},{"id":"2512.16029","title":"Cross-Language Bias Examination in Large Language Models","created":"2025-12-17","cited_by_count":1,"area":null},{"id":"2601.09141","title":"Identity-Robust Language Model Generation via Content Integrity Preservation","created":"2026-01-14","cited_by_count":1,"area":null},{"id":"2602.00300","title":"Faithful-Patchscopes: Understanding and Mitigating Model Bias in Hidden Representations Explanation of Large Language Models","created":"2026-01-30","cited_by_count":1,"area":null},{"id":"2602.04306","title":"DeFrame: Debiasing Large Language Models Against Framing Effects","created":"2026-02-04","cited_by_count":1,"area":null},{"id":"2603.27141","title":"Routing Sensitivity Without Controllability: A Diagnostic Study of Fairness in MoE Language Models","created":"2026-03-28","cited_by_count":1,"area":"moe"},{"id":"2411.12590","title":"Debias your Large Multi-Modal Model at Test-Time via Non-Contrastive Visual Attribute Steering","created":"2024-11-15","cited_by_count":0,"area":"mllm"},{"id":"2503.19426","title":"DeCAP: Context-Adaptive Prompt Generation for Debiasing Zero-shot Question Answering in Large Language Models","created":"2025-03-25","cited_by_count":0,"area":null},{"id":"2510.10142","title":"Debiasing LLMs by Masking Unfairness-Driving Attention Heads","created":"2025-10-11","cited_by_count":0,"area":null},{"id":"2601.21864","title":"Knowing Bias, Doing Better: Mitigating Social Bias in LLMs via Know-Bias Neuron Enhancement","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2603.19144","title":"UGID: Unified Graph Isomorphism for Debiasing Large Language Models","created":"2026-03-19","cited_by_count":0,"area":null},{"id":"2603.27057","title":"Debiasing Large Language Models toward Social Factors in Online Behavior Analytics through Prompt Knowledge Tuning","created":"2026-03-28","cited_by_count":0,"area":null},{"id":"2606.30989","title":"Wait, am I Being Fair? Characterizing Deductive Stereotyping and Mitigating It with Fair-GCG","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2608.21415","title":"Mitigating Bias in Large Vision-Language Models via Counterfactual Ensemble Decoding","created":"2026-08-12","cited_by_count":0,"area":"mllm"},{"id":"2609.40124","title":"Debias It Yourself: Teaching LLMs Cognitive Bias Mitigation Interventions","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.03240","title":"Collective Bias Mitigation via Model Routing and Collaboration","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}