{"total":55,"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":"2308.01263","title":"XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models","created":"2023-08-02","cited_by_count":505,"area":null},{"id":"2401.14887","title":"The Power of Noise: Redefining Retrieval for RAG Systems","created":"2024-01-26","cited_by_count":281,"area":"rag"},{"id":"2308.10149","title":"A Survey on Fairness in Large Language Models","created":"2023-08-20","cited_by_count":95,"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":"2306.08645","title":"Training-free Diffusion Model Adaptation for Variable-Sized Text-to-Image Synthesis","created":"2023-06-14","cited_by_count":56,"area":"diffusion"},{"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":"2412.16545","title":"Attention Entropy is a Key Factor: An Analysis of Parallel Context Encoding with Full-attention-based Pre-trained Language Models","created":"2024-12-21","cited_by_count":26,"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":"2406.05392","title":"Deconstructing The Ethics of Large Language Models from Long-standing Issues to New-emerging Dilemmas: A Survey","created":"2024-06-08","cited_by_count":23,"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":"2408.06518","title":"Does Liking Yellow Imply Driving a School Bus? Semantic Leakage in Language Models","created":"2024-08-12","cited_by_count":15,"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":"2503.17675","title":"Towards Transformer-Based Aligned Generation with Self-Coherence Guidance","created":"2025-03-22","cited_by_count":14,"area":"diffusion"},{"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":"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":"2405.16504","title":"Explaining Modern Gated-Linear RNNs via a Unified Implicit Attention Formulation","created":"2024-05-26","cited_by_count":11,"area":"ssm"},{"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":"2305.17627","title":"Robust Natural Language Understanding with Residual Attention Debiasing","created":"2023-05-28","cited_by_count":10,"area":null},{"id":"2309.02311","title":"Weigh Your Own Words: Improving Hate Speech Counter Narrative Generation via Attention Regularization","created":"2023-09-05","cited_by_count":7,"area":null},{"id":"2409.17929","title":"The Lou Dataset -- Exploring the Impact of Gender-Fair Language in German Text Classification","created":"2024-09-26","cited_by_count":5,"area":null},{"id":"2410.16327","title":"Feint and Attack: Attention-Based Strategies for Jailbreaking and Protecting LLMs","created":"2024-10-18","cited_by_count":5,"area":"safety"},{"id":"2601.03481","title":"Self-Explaining Hate Speech Detection with Moral Rationales","created":"2026-01-07","cited_by_count":5,"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":"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":"2312.08916","title":"Progressive Feature Self-reinforcement for Weakly Supervised Semantic Segmentation","created":"2023-12-14","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":"2601.17958","title":"TensorLens: End-to-End Transformer Analysis via High-Order Attention Tensors","created":"2026-01-25","cited_by_count":3,"area":null},{"id":"2310.03240","title":"Learning Hierarchical Relational Representations through Relational Convolutions","created":"2023-10-05","cited_by_count":2,"area":null},{"id":"2403.10774","title":"Detecting Bias in Large Language Models: Fine-tuned KcBERT","created":"2024-03-16","cited_by_count":2,"area":null},{"id":"2404.04838","title":"Data Bias According to Bipol: Men are Naturally Right and It is the Role of Women to Follow Their Lead","created":"2024-04-07","cited_by_count":2,"area":null},{"id":"2406.04146","title":"Towards Understanding Task-agnostic Debiasing Through the Lenses of Intrinsic Bias and Forgetfulness","created":"2024-06-06","cited_by_count":2,"area":null},{"id":"2409.20204","title":"Divided by discipline? A systematic literature review on the quantification of online sexism and misogyny using a semi-automated approach","created":"2024-09-30","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":"2502.01472","title":"FALCON: Fine-grained Activation Manipulation by Contrastive Orthogonal Unalignment for Large Language Model","created":"2025-02-03","cited_by_count":1,"area":"alignment"},{"id":"2503.12931","title":"MirrorShield: Towards Universal Defense Against Jailbreaks via Entropy-Guided Mirror Crafting","created":"2025-03-17","cited_by_count":1,"area":"safety"},{"id":"2506.22481","title":"Theories of \"Sexuality\" in Natural Language Processing Bias Research","created":"2025-06-22","cited_by_count":1,"area":null},{"id":"2511.16353","title":"Learning from Sufficient Rationales: Analysing the Relationship Between Explanation Faithfulness and Token-level Regularisation Strategies","created":"2025-11-20","cited_by_count":1,"area":null},{"id":"2511.20698","title":"On the Role of Hidden States of Modern Hopfield Network in Transformer","created":"2025-11-24","cited_by_count":1,"area":null},{"id":"2602.17636","title":"CORAL: Correspondence Alignment for Improved Virtual Try-On","created":"2026-02-19","cited_by_count":1,"area":null},{"id":"2209.08681","title":"Domain Classification-based Source-specific Term Penalization for Domain Adaptation in Hate-speech Detection","created":"2022-09-18","cited_by_count":0,"area":null},{"id":"2210.09340","title":"Transferring Knowledge via Neighborhood-Aware Optimal Transport for Low-Resource Hate Speech Detection","created":"2022-10-17","cited_by_count":0,"area":null},{"id":"2309.00751","title":"Let the Models Respond: Interpreting Language Model Detoxification Through the Lens of Prompt Dependence","created":"2023-09-01","cited_by_count":0,"area":null},{"id":"2407.01697","title":"NLPGuard: A Framework for Mitigating the Use of Protected Attributes by NLP Classifiers","created":"2024-07-01","cited_by_count":0,"area":null},{"id":"2501.19337","title":"Token-Level Entropy Reveals Demographic Disparities in Large Language Models","created":"2025-01-31","cited_by_count":0,"area":null},{"id":"2506.12148","title":"Hatevolution: What Static Benchmarks Don't Tell Us","created":"2025-06-13","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":"2509.13651","title":"Controllable Pareto Trade-off between Fairness and Accuracy","created":"2025-09-17","cited_by_count":0,"area":null},{"id":"2509.22291","title":"Bridging Fairness and Explainability: Can Input-Based Explanations Promote Fairness in Hate Speech Detection?","created":"2025-09-26","cited_by_count":0,"area":null},{"id":"2511.10120","title":"Generalizing to Unseen Disaster Events: A Causal View","created":"2025-11-13","cited_by_count":0,"area":null},{"id":"2604.03803","title":"R\\'enyi Attention Entropy for Patch Pruning","created":"2026-04-04","cited_by_count":0,"area":null},{"id":"2604.10504","title":"CARO: Chain-of-Analogy Reasoning Optimization for Robust Content Moderation","created":"2026-04-12","cited_by_count":0,"area":"lr"},{"id":"2604.16654","title":"IYKYK (But AI Doesn't): Automated Content Moderation Does Not Capture Communities' Heterogeneous Attitudes Towards Reclaimed Language","created":"2026-04-17","cited_by_count":0,"area":null},{"id":"2604.26188","title":"Efficient and Interpretable Transformer for Counterfactual Fairness","created":"2026-04-29","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}