{"total":124,"rows":[{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588,"area":null},{"id":"2412.16720","title":"OpenAI o1 System Card","created":"2024-12-21","cited_by_count":1244,"area":"lr"},{"id":"2402.10373","title":"BioMistral: A Collection of Open-Source Pretrained Large Language Models for Medical Domains","created":"2024-02-15","cited_by_count":301,"area":null},{"id":"2402.08787","title":"Rethinking Machine Unlearning for Large Language Models","created":"2024-02-13","cited_by_count":257,"area":"lr"},{"id":"2401.06080","title":"Secrets of RLHF in Large Language Models Part II: Reward Modeling","created":"2024-01-11","cited_by_count":171,"area":"alignment"},{"id":"2505.23836","title":"Large Language Models Often Know When They Are Being Evaluated","created":"2025-05-28","cited_by_count":128,"area":null},{"id":"2404.05399","title":"SafetyPrompts: a Systematic Review of Open Datasets for Evaluating and Improving Large Language Model Safety","created":"2024-04-08","cited_by_count":77,"area":"safety"},{"id":"2406.11050","title":"A Peek into Token Bias: Large Language Models Are Not Yet Genuine Reasoners","created":"2024-06-16","cited_by_count":73,"area":"lr"},{"id":"2501.08156","title":"Are DeepSeek R1 And Other Reasoning Models More Faithful?","created":"2025-01-14","cited_by_count":72,"area":"lr"},{"id":"2504.18412","title":"Expressing stigma and inappropriate responses prevents LLMs from safely replacing mental health providers","created":"2025-04-25","cited_by_count":69,"area":null},{"id":"2502.08640","title":"Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs","created":"2025-02-12","cited_by_count":67,"area":"agents"},{"id":"2404.12241","title":"Introducing v0.5 of the AI Safety Benchmark from MLCommons","created":"2024-04-18","cited_by_count":62,"area":null},{"id":"2407.21792","title":"Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress?","created":"2024-07-31","cited_by_count":61,"area":null},{"id":"2402.04105","title":"Measuring Implicit Bias in Explicitly Unbiased Large Language Models","created":"2024-02-06","cited_by_count":51,"area":null},{"id":"2407.20516","title":"Machine Unlearning in Generative AI: A Survey","created":"2024-07-30","cited_by_count":49,"area":"safety"},{"id":"2501.09620","title":"Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment","created":"2025-01-16","cited_by_count":42,"area":"alignment"},{"id":"2402.07282","title":"How do Large Language Models Navigate Conflicts between Honesty and Helpfulness?","created":"2024-02-11","cited_by_count":27,"area":null},{"id":"2407.14614","title":"Evaluating language models as risk scores","created":"2024-07-19","cited_by_count":27,"area":null},{"id":"2406.10486","title":"Do Large Language Models Discriminate in Hiring Decisions on the Basis of Race, Ethnicity, and Gender?","created":"2024-06-15","cited_by_count":25,"area":null},{"id":"2402.10688","title":"Towards Uncovering How Large Language Model Works: An Explainability Perspective","created":"2024-02-16","cited_by_count":22,"area":"lr"},{"id":"2404.10160","title":"Reinforcement Learning from Multi-role Debates as Feedback for Bias Mitigation in LLMs","created":"2024-04-15","cited_by_count":22,"area":"alignment"},{"id":"2406.03198","title":"The Impossibility of Fair LLMs","created":"2024-05-28","cited_by_count":22,"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":"2404.03086","title":"Auditing the Use of Language Models to Guide Hiring Decisions","created":"2024-04-03","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":"2502.01926","title":"Fairness through Difference Awareness: Measuring Desired Group Discrimination in LLMs","created":"2025-02-04","cited_by_count":20,"area":null},{"id":"2505.21091","title":"Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs)","created":"2025-05-27","cited_by_count":19,"area":null},{"id":"2506.10922","title":"Robustly Improving LLM Fairness in Realistic Settings via Interpretability","created":"2025-06-12","cited_by_count":18,"area":null},{"id":"2410.17519","title":"Large Language Models Still Exhibit Bias in Long Text","created":"2024-10-23","cited_by_count":16,"area":null},{"id":"2503.19182","title":"Evaluating Bias in LLMs for Job-Resume Matching: Gender, Race, and Education","created":"2025-03-24","cited_by_count":14,"area":null},{"id":"2409.04340","title":"AGR: Age Group fairness Reward for Bias Mitigation in LLMs","created":"2024-09-06","cited_by_count":12,"area":"alignment"},{"id":"2409.09041","title":"Acceptable Use Policies for Foundation Models","created":"2024-08-29","cited_by_count":12,"area":null},{"id":"2407.18454","title":"Fairness Definitions in Language Models Explained","created":"2024-07-26","cited_by_count":11,"area":null},{"id":"2503.01742","title":"Building Safe GenAI Applications: An End-to-End Overview of Red Teaming for Large Language Models","created":"2025-03-03","cited_by_count":11,"area":"safety"},{"id":"2509.11620","title":"AesBiasBench: Evaluating Bias and Alignment in Multimodal Language Models for Personalized Image Aesthetic Assessment","created":"2025-09-15","cited_by_count":11,"area":"mllm"},{"id":"2502.18156","title":"Can LLMs Explain Themselves Counterfactually?","created":"2025-02-25","cited_by_count":10,"area":null},{"id":"2508.15830","title":"DAIQ: Auditing Demographic Attribute Inference from Question in LLMs","created":"2025-08-18","cited_by_count":10,"area":null},{"id":"2410.22118","title":"The Impact of Inference Acceleration on Bias of LLMs","created":"2024-10-29","cited_by_count":9,"area":"inference"},{"id":"2507.11344","title":"Guiding LLM Decision-Making with Fairness Reward Models","created":"2025-07-15","cited_by_count":9,"area":"lr"},{"id":"2601.18572","title":"One Persona, Many Cues, Different Results: How Sociodemographic Cues Impact LLM Personalization","created":"2026-01-26","cited_by_count":9,"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":"2406.18534","title":"Towards Compositionality in Concept Learning","created":"2024-06-26","cited_by_count":7,"area":null},{"id":"2407.19760","title":"Legal Minds, Algorithmic Decisions: How LLMs Apply Constitutional Principles in Complex Scenarios","created":"2024-07-29","cited_by_count":7,"area":null},{"id":"2409.11149","title":"SAGED: A Holistic Bias-Benchmarking Pipeline for Language Models with Customisable Fairness Calibration","created":"2024-09-17","cited_by_count":6,"area":null},{"id":"2412.04642","title":"Improving LLM Group Fairness on Tabular Data via In-Context Learning","created":"2024-12-05","cited_by_count":6,"area":null},{"id":"2505.12349","title":"Wisdom from Diversity: Bias Mitigation Through Hybrid Human-LLM Crowds","created":"2025-05-18","cited_by_count":6,"area":null},{"id":"2510.23751","title":"Debiasing Reward Models by Representation Learning with Guarantees","created":"2025-10-27","cited_by_count":6,"area":"alignment"},{"id":"2602.15456","title":"In Agents We Trust, but Who Do Agents Trust? Latent Source Preferences Steer LLM Generations","created":"2026-02-17","cited_by_count":6,"area":"agents"},{"id":"2402.01821","title":"Human-like Category Learning by Injecting Ecological Priors from Large Language Models into Neural Networks","created":"2024-02-02","cited_by_count":5,"area":null},{"id":"2404.07475","title":"Laissez-Faire Harms: Algorithmic Biases in Generative Language Models","created":"2024-04-11","cited_by_count":5,"area":null},{"id":"2409.18203","title":"Policy Maps: Tools for Guiding the Unbounded Space of LLM Behaviors","created":"2024-09-26","cited_by_count":5,"area":null},{"id":"2411.03700","title":"The Root Shapes the Fruit: On the Persistence of Gender-Exclusive Harms in Aligned Language Models","created":"2024-11-06","cited_by_count":5,"area":"alignment"},{"id":"2504.06303","title":"On the Effectiveness and Generalization of Race Representations for Debiasing High-Stakes Decisions","created":"2025-04-07","cited_by_count":5,"area":null},{"id":"2505.04038","title":"Identities are not Interchangeable: The Problem of Overgeneralization in Fair Machine Learning","created":"2025-05-07","cited_by_count":5,"area":null},{"id":"2510.09871","title":"CoBia: Constructed Conversations Can Trigger Otherwise Concealed Societal Biases in LLMs","created":"2025-10-10","cited_by_count":5,"area":"safety"},{"id":"2605.01048","title":"Compared to What? Baselines and Metrics for Counterfactual Prompting","created":"2026-05-01","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":"2506.03867","title":"EuroGEST: Investigating gender stereotypes in multilingual language models","created":"2025-06-04","cited_by_count":4,"area":null},{"id":"2508.18088","title":"How Quantization Shapes Bias in Large Language Models","created":"2025-08-25","cited_by_count":4,"area":null},{"id":"2601.18486","title":"Different Demographic Cues Yield Inconsistent Conclusions About LLM Personalization and Bias","created":"2026-01-26","cited_by_count":4,"area":null},{"id":"2406.07685","title":"Test-Time Fairness and Robustness in Large Language Models","created":"2024-06-11","cited_by_count":3,"area":null},{"id":"2406.16738","title":"Inducing Group Fairness in Prompt-Based Language Model Decisions","created":"2024-06-24","cited_by_count":3,"area":null},{"id":"2408.01285","title":"Do Prevalent Bias Metrics Capture Allocational Harms from LLMs?","created":"2024-08-02","cited_by_count":3,"area":null},{"id":"2412.04576","title":"Show, Don't Tell: Uncovering Implicit Character Portrayal using LLMs","created":"2024-12-05","cited_by_count":3,"area":null},{"id":"2501.14294","title":"Examining Alignment of Large Language Models through Representative Heuristics: The Case of Political Stereotypes","created":"2025-01-24","cited_by_count":3,"area":"alignment"},{"id":"2504.06549","title":"Societal Impacts Research Requires Benchmarks for Creative Composition Tasks","created":"2025-04-09","cited_by_count":3,"area":null},{"id":"2506.19028","title":"Quantifying Fairness in LLMs Beyond Tokens: A Semantic and Statistical Perspective","created":"2025-06-23","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":"2510.06222","title":"Inducing State Anxiety in LLM Agents Reproduces Human-Like Biases in Consumer Decision-Making","created":"2025-08-30","cited_by_count":3,"area":"agents"},{"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":"2602.16729","title":"Intent Laundering: AI Safety Datasets Are Not What They Seem","created":"2026-02-17","cited_by_count":3,"area":null},{"id":"2604.08525","title":"Ads in AI Chatbots? An Analysis of How Large Language Models Navigate Conflicts of Interest","created":"2026-04-09","cited_by_count":3,"area":null},{"id":"2606.16723","title":"AgentFairBench: Do LLM Agents Discriminate When They Act?","created":"2026-06-15","cited_by_count":3,"area":"agents"},{"id":"2406.06407","title":"A Taxonomy of Challenges to Curating Fair Datasets","created":"2024-06-10","cited_by_count":2,"area":null},{"id":"2409.14583","title":"LLM Bias Evaluation: Gender, Racial, and Age Disparities in Occupational and Crime Scenarios","created":"2024-09-22","cited_by_count":2,"area":null},{"id":"2501.06248","title":"Utility-inspired Reward Transformations Improve Reinforcement Learning Training of Language Models","created":"2025-01-08","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":"2511.06148","title":"Large Language Models Develop Novel Social Biases Through Adaptive Exploration","created":"2025-11-08","cited_by_count":2,"area":null},{"id":"2602.03263","title":"CSR-Bench: A Benchmark for Evaluating the Cross-modal Safety and Reliability of MLLMs","created":"2026-02-03","cited_by_count":2,"area":"mllm"},{"id":"2602.13253","title":"Implicit Bias in LLMs for Transgender Populations","created":"2026-02-02","cited_by_count":2,"area":null},{"id":"2605.06901","title":"Reflections and New Directions for Human-Centered Large Language Models","created":"2026-05-07","cited_by_count":2,"area":null},{"id":"2606.02776","title":"Topics as Proxies for Sociodemographics: How Conversational Context Affects LLM Answers","created":"2026-06-01","cited_by_count":2,"area":null},{"id":"2607.28934","title":"FairFund-Bench: Evaluating Distributive Bias in LLM Resource Allocation","created":"2026-07-31","cited_by_count":2,"area":null},{"id":"2410.04472","title":"Collapsed Language Models Promote Fairness","created":"2024-10-06","cited_by_count":1,"area":null},{"id":"2501.04316","title":"Small Changes, Large Consequences: Analyzing the Allocational Fairness of LLMs in Hiring Contexts","created":"2025-01-08","cited_by_count":1,"area":null},{"id":"2505.12054","title":"GenderBench: Evaluation Suite for Gender Biases in LLMs","created":"2025-05-17","cited_by_count":1,"area":null},{"id":"2511.10695","title":"\"As Eastern Powers, I will veto.\" : An Investigation of Nation-level Bias of Large Language Models in International Relations","created":"2025-11-12","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":"2604.08963","title":"Aligned Agents, Biased Swarm: Measuring Bias Amplification in Multi-Agent Systems","created":"2026-04-10","cited_by_count":1,"area":null},{"id":"2607.22570","title":"Reference Feature Atlases for Mechanistic Auditing of Language Models","created":"2026-06-01","cited_by_count":1,"area":null},{"id":"2411.16730","title":"\"Moralized\" Multi-Step Jailbreak Prompts: Black-Box Testing of Guardrails in Large Language Models for Verbal Attacks","created":"2024-11-23","cited_by_count":0,"area":"safety"},{"id":"2505.18236","title":"From Bias to Accountability: How the EU AI Act Confronts Challenges in European GeoAI Auditing","created":"2025-05-23","cited_by_count":0,"area":null},{"id":"2509.09735","title":"Discrimination by LLMs: Cross-lingual Bias Assessment and Mitigation in Decision-Making and Summarisation","created":"2025-09-10","cited_by_count":0,"area":null},{"id":"2512.05243","title":"Decoding the Black Box: Discerning AI Rhetorics About and Through Poetic Prompting","created":"2025-12-04","cited_by_count":0,"area":null},{"id":"2601.16398","title":"White-Box Sensitivity Auditing with Steering Vectors","created":"2026-01-23","cited_by_count":0,"area":"mechinterp"},{"id":"2602.11924","title":"Who Does What? Archetypes of Roles Assigned to LLMs During Human-AI Decision-Making","created":"2026-02-12","cited_by_count":0,"area":null},{"id":"2602.15338","title":"Discovering Implicit Large Language Model Alignment Objectives","created":"2026-02-17","cited_by_count":0,"area":"alignment"},{"id":"2604.01925","title":"ImplicitBBQ: Benchmarking Implicit Bias in Large Language Models through Characteristic Based Cues","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2604.12500","title":"Safety Training Modulates Harmful Misalignment Under On-Policy RL, But Direction Depends on Environment Design","created":"2026-04-14","cited_by_count":0,"area":null}],"next_cursor":"100"}