{"total":184,"rows":[{"id":"2409.05907","title":"Programming Refusal with Conditional Activation Steering","created":"2024-09-06","cited_by_count":206,"area":"mechinterp"},{"id":"2408.10075","title":"Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learning","created":"2024-08-19","cited_by_count":155,"area":"alignment"},{"id":"2404.16019","title":"The PRISM Alignment Dataset: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models","created":"2024-04-24","cited_by_count":144,"area":"alignment"},{"id":"2406.15951","title":"Modular Pluralism: Pluralistic Alignment via Multi-LLM Collaboration","created":"2024-06-22","cited_by_count":113,"area":"alignment"},{"id":"2405.20304","title":"Group Robust Preference Optimization in Reward-free RLHF","created":"2024-05-30","cited_by_count":95,"area":"lr"},{"id":"2405.17977","title":"Aligning to Thousands of Preferences via System Message Generalization","created":"2024-05-28","cited_by_count":84,"area":"alignment"},{"id":"2410.24190","title":"Hidden Persuaders: LLMs' Political Leaning and Their Influence on Voters","created":"2024-10-31","cited_by_count":71,"area":null},{"id":"2502.16761","title":"Language Model Fine-Tuning on Scaled Survey Data for Predicting Distributions of Public Opinions","created":"2025-02-24","cited_by_count":66,"area":null},{"id":"2411.05403","title":"Benchmarking Distributional Alignment of Large Language Models","created":"2024-11-08","cited_by_count":61,"area":"alignment"},{"id":"2410.04070","title":"PAD: Personalized Alignment of LLMs at Decoding-Time","created":"2024-10-05","cited_by_count":60,"area":"alignment"},{"id":"2404.10199","title":"CULTURE-GEN: Revealing Global Cultural Perception in Language Models through Natural Language Prompting","created":"2024-04-16","cited_by_count":55,"area":null},{"id":"2406.08469","title":"PAL: Pluralistic Alignment Framework for Learning from Heterogeneous Preferences","created":"2024-06-12","cited_by_count":54,"area":"alignment"},{"id":"2410.14632","title":"Diverging Preferences: When do Annotators Disagree and do Models Know?","created":"2024-10-18","cited_by_count":47,"area":"alignment"},{"id":"2407.02273","title":"Language Model Alignment in Multilingual Trolley Problems","created":"2024-07-02","cited_by_count":46,"area":"alignment"},{"id":"2410.01639","title":"Moral Alignment for LLM Agents","created":"2024-10-02","cited_by_count":39,"area":"agents"},{"id":"2504.14439","title":"LoRe: Personalizing LLMs via Low-Rank Reward Modeling","created":"2025-04-20","cited_by_count":38,"area":"alignment"},{"id":"2508.01491","title":"The Homogenizing Effect of Large Language Models on Human Expression and Thought","created":"2025-08-02","cited_by_count":35,"area":"lr"},{"id":"2410.03868","title":"Can Language Models Reason about Individualistic Human Values and Preferences?","created":"2024-10-04","cited_by_count":34,"area":"lr"},{"id":"2406.17692","title":"From Distributional to Overton Pluralism: Investigating Large Language Model Alignment","created":"2024-06-25","cited_by_count":33,"area":"alignment"},{"id":"2503.06358","title":"Language Model Personalization via Reward Factorization","created":"2025-03-08","cited_by_count":31,"area":"alignment"},{"id":"2411.12405","title":"Evaluating the Prompt Steerability of Large Language Models","created":"2024-11-19","cited_by_count":27,"area":null},{"id":"2510.26202","title":"What's In My Human Feedback? Learning Interpretable Descriptions of Preference Data","created":"2025-10-30","cited_by_count":26,"area":"alignment"},{"id":"2412.07951","title":"From Lived Experience to Insight: Unpacking the Psychological Risks of Using AI Conversational Agents","created":"2024-12-10","cited_by_count":25,"area":null},{"id":"2502.20502","title":"On Benchmarking Human-Like Intelligence in Machines","created":"2025-02-27","cited_by_count":25,"area":null},{"id":"2406.11191","title":"A Survey on Human Preference Learning for Large Language Models","created":"2024-06-17","cited_by_count":24,"area":"alignment"},{"id":"2407.02209","title":"Generative Monoculture in Large Language Models","created":"2024-07-02","cited_by_count":22,"area":null},{"id":"2407.14916","title":"Improving Context-Aware Preference Modeling for Language Models","created":"2024-07-20","cited_by_count":22,"area":"alignment"},{"id":"2501.06655","title":"Personalized Preference Fine-tuning of Diffusion Models","created":"2025-01-11","cited_by_count":22,"area":"diffusion"},{"id":"2508.01674","title":"CUPID: Evaluating Personalized and Contextualized Alignment of LLMs from Interactions","created":"2025-08-03","cited_by_count":22,"area":null},{"id":"2412.20299","title":"No Preference Left Behind: Group Distributional Preference Optimization","created":"2024-12-28","cited_by_count":21,"area":"alignment"},{"id":"2506.01080","title":"The Coming Crisis of Multi-Agent Misalignment: AI Alignment Must Be a Dynamic and Social Process","created":"2025-06-01","cited_by_count":21,"area":"alignment"},{"id":"2409.09586","title":"ValueCompass: A Framework for Measuring Contextual Value Alignment Between Human and LLMs","created":"2024-09-15","cited_by_count":20,"area":"alignment"},{"id":"2502.10441","title":"AI Alignment at Your Discretion","created":"2025-02-10","cited_by_count":20,"area":null},{"id":"2402.14147","title":"Wikibench: Community-Driven Data Curation for AI Evaluation on Wikipedia","created":"2024-02-21","cited_by_count":18,"area":null},{"id":"2406.09264","title":"Position: Towards Bidirectional Human-AI Alignment","created":"2024-06-13","cited_by_count":18,"area":"alignment"},{"id":"2411.11072","title":"Multilingual Large Language Models: A Systematic Survey","created":"2024-11-17","cited_by_count":18,"area":null},{"id":"2505.14633","title":"Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas","created":"2025-05-20","cited_by_count":18,"area":null},{"id":"2505.16869","title":"MPO: Multilingual Safety Alignment via Reward Gap Optimization","created":"2025-05-22","cited_by_count":18,"area":"alignment"},{"id":"2409.17213","title":"Plurals: A System for Guiding LLMs Via Simulated Social Ensembles","created":"2024-09-25","cited_by_count":17,"area":null},{"id":"2506.12152","title":"Because we have LLMs, we Can and Should Pursue Agentic Interpretability","created":"2025-06-13","cited_by_count":16,"area":"agents"},{"id":"2406.04064","title":"Ask LLMs Directly, \"What shapes your bias?\": Measuring Social Bias in Large Language Models","created":"2024-06-06","cited_by_count":14,"area":null},{"id":"2503.09925","title":"PluralLLM: Pluralistic Alignment in LLMs via Federated Learning","created":"2025-03-13","cited_by_count":14,"area":"alignment"},{"id":"2504.01205","title":"Epistemic Alignment: A Mediating Framework for User-LLM Knowledge Delivery","created":"2025-04-01","cited_by_count":14,"area":null},{"id":"2506.06298","title":"Pairwise Calibrated Rewards for Pluralistic Alignment","created":"2025-05-17","cited_by_count":14,"area":"alignment"},{"id":"2405.02411","title":"The Call for Socially Aware Language Technologies","created":"2024-05-03","cited_by_count":13,"area":null},{"id":"2502.15861","title":"C3AI: Crafting and Evaluating Constitutions for Constitutional AI","created":"2025-02-21","cited_by_count":13,"area":"alignment"},{"id":"2506.06958","title":"Simulating Society Requires Simulating Thought","created":"2025-06-08","cited_by_count":13,"area":"lr"},{"id":"2601.04583","title":"Autonomous Agents on Blockchains: Standards, Execution Models, and Trust Boundaries","created":"2026-01-08","cited_by_count":13,"area":"agents"},{"id":"2507.07341","title":"On the Impossibility of Separating Intelligence from Judgment: The Computational Intractability of Filtering for AI Alignment","created":"2025-07-09","cited_by_count":12,"area":"safety"},{"id":"2409.18110","title":"Open-World Evaluation for Retrieving Diverse Perspectives","created":"2024-09-26","cited_by_count":11,"area":null},{"id":"2412.03822","title":"Beyond the Binary: Capturing Diverse Preferences With Reward Regularization","created":"2024-12-05","cited_by_count":11,"area":"alignment"},{"id":"2412.06483","title":"SafeWorld: Geo-Diverse Safety Alignment","created":"2024-12-09","cited_by_count":11,"area":"wm"},{"id":"2412.08812","title":"Test-Time Alignment via Hypothesis Reweighting","created":"2024-12-11","cited_by_count":11,"area":"alignment"},{"id":"2504.12663","title":"Persona-judge: Personalized Alignment of Large Language Models via Token-level Self-judgment","created":"2025-04-17","cited_by_count":11,"area":"alignment"},{"id":"2403.09704","title":"Alignment Studio: Aligning Large Language Models to Particular Contextual Regulations","created":"2024-03-08","cited_by_count":10,"area":"alignment"},{"id":"2410.16665","title":"SafetyAnalyst: Interpretable, Transparent, and Steerable Safety Moderation for AI Behavior","created":"2024-10-22","cited_by_count":10,"area":null},{"id":"2503.01658","title":"CoPL: Collaborative Preference Learning for Personalizing LLMs","created":"2025-03-03","cited_by_count":10,"area":"alignment"},{"id":"2505.21548","title":"Fluent but Foreign: Even Regional LLMs Lack Cultural Alignment","created":"2025-05-25","cited_by_count":10,"area":null},{"id":"2506.07326","title":"Reward Model Interpretability via Optimal and Pessimal Tokens","created":"2025-06-08","cited_by_count":10,"area":"alignment"},{"id":"2506.20702","title":"The Singapore Consensus on Global AI Safety Research Priorities","created":"2025-06-25","cited_by_count":10,"area":null},{"id":"2507.13579","title":"Learning to summarize user information for personalized reinforcement learning from human feedback","created":"2025-07-17","cited_by_count":10,"area":"alignment"},{"id":"2511.21322","title":"TALES: A Taxonomy and Analysis of Cultural Representations in LLM-generated Stories","created":"2025-11-26","cited_by_count":10,"area":null},{"id":"2402.07214","title":"Through the Lens of Split Vote: Exploring Disagreement, Difficulty and Calibration in Legal Case Outcome Classification","created":"2024-02-11","cited_by_count":9,"area":null},{"id":"2408.05094","title":"Unlocking Decoding-time Controllability: Gradient-Free Multi-Objective Alignment with Contrastive Prompts","created":"2024-08-09","cited_by_count":9,"area":"alignment"},{"id":"2410.11055","title":"Varying Shades of Wrong: Aligning LLMs with Wrong Answers Only","created":"2024-10-14","cited_by_count":9,"area":"alignment"},{"id":"2501.09254","title":"Clone-Robust AI Alignment","created":"2025-01-16","cited_by_count":9,"area":"alignment"},{"id":"2503.08796","title":"Robust Multi-Objective Controlled Decoding of Large Language Models","created":"2025-03-11","cited_by_count":9,"area":null},{"id":"2505.18139","title":"Embracing Contradiction: Theoretical Inconsistency Will Not Impede the Road of Building Responsible AI Systems","created":"2025-05-23","cited_by_count":8,"area":null},{"id":"2603.06495","title":"COLD-Steer: Steering Large Language Models via In-Context One-step Learning Dynamics","created":"2026-03-06","cited_by_count":8,"area":"mechinterp"},{"id":"2408.03459","title":"Can DPO Learn Diverse Human Values? A Theoretical Scaling Law","created":"2024-08-06","cited_by_count":7,"area":"alignment"},{"id":"2507.13158","title":"Inverse Reinforcement Learning Meets Large Language Model Post-Training: Basics, Advances, and Opportunities","created":"2025-07-17","cited_by_count":7,"area":"alignment"},{"id":"2602.11328","title":"Evaluating Alignment of Behavioral Dispositions in LLMs","created":"2026-02-11","cited_by_count":7,"area":"alignment"},{"id":"2603.09970","title":"CREATE: Testing LLMs for Associative Creativity","created":"2026-03-10","cited_by_count":7,"area":null},{"id":"2604.07343","title":"Personalized RewardBench: Evaluating Reward Models with Human Aligned Personalization","created":"2026-04-08","cited_by_count":7,"area":"alignment"},{"id":"2512.05671","title":"ClinTutor-R1: Advancing Scalable and Robust One-to-Many Alignment in Clinical Socratic Education","created":"2025-12-05","cited_by_count":6,"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":"2503.09561","title":"Strategyproof Reinforcement Learning from Human Feedback","created":"2025-03-12","cited_by_count":5,"area":"alignment"},{"id":"2503.16094","title":"Cultural Alignment in Large Language Models Using Soft Prompt Tuning","created":"2025-03-20","cited_by_count":5,"area":"alignment"},{"id":"2505.21537","title":"OpenReview Should be Protected and Leveraged as a Community Asset for Research in the Era of Large Language Models","created":"2025-05-24","cited_by_count":5,"area":null},{"id":"2601.08951","title":"PluriHarms: Benchmarking the Full Spectrum of Human Judgments on AI Harm","created":"2026-01-13","cited_by_count":5,"area":null},{"id":"2603.12595","title":"Swap-guided Preference Learning for Personalized Reinforcement Learning from Human Feedback","created":"2026-03-13","cited_by_count":5,"area":"alignment"},{"id":"2605.10310","title":"Positive Alignment: Artificial Intelligence for Human Flourishing","created":"2026-05-11","cited_by_count":5,"area":null},{"id":"2406.03642","title":"Is Free Self-Alignment Possible?","created":"2024-06-05","cited_by_count":4,"area":"alignment"},{"id":"2408.10392","title":"Value Alignment from Unstructured Text","created":"2024-08-19","cited_by_count":4,"area":"alignment"},{"id":"2410.11221","title":"Multi-objective Reinforcement Learning: A Tool for Pluralistic Alignment","created":"2024-10-15","cited_by_count":4,"area":null},{"id":"2412.13998","title":"Few-shot Steerable Alignment: Adapting Rewards and LLM Policies with Neural Processes","created":"2024-12-18","cited_by_count":4,"area":"alignment"},{"id":"2506.05619","title":"Beyond RLHF and NLHF: Population-Proportional Alignment under an Axiomatic Framework","created":"2025-06-05","cited_by_count":4,"area":"alignment"},{"id":"2506.20209","title":"Perspectives in Play: A Multi-Perspective Approach for More Inclusive NLP Systems","created":"2025-06-25","cited_by_count":4,"area":null},{"id":"2511.19458","title":"Personalized Reward Modeling for Text-to-Image Generation","created":"2025-11-21","cited_by_count":4,"area":"alignment"},{"id":"2406.14903","title":"GIEBench: Towards Holistic Evaluation of Group Identity-based Empathy for Large Language Models","created":"2024-06-21","cited_by_count":3,"area":null},{"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":"2504.06549","title":"Societal Impacts Research Requires Benchmarks for Creative Composition Tasks","created":"2025-04-09","cited_by_count":3,"area":null},{"id":"2504.10359","title":"DICE: A Framework for Dimensional and Contextual Evaluation of Language Models","created":"2025-04-14","cited_by_count":3,"area":null},{"id":"2508.16982","title":"Decoding Alignment: A Critical Survey of LLM Development Initiatives through Value-setting and Data-centric Lens","created":"2025-08-23","cited_by_count":3,"area":"alignment"},{"id":"2509.21712","title":"It's My Agent, Not Me: Personal Privacy Boundaries in AI-Delegated Information Sharing","created":"2025-09-26","cited_by_count":3,"area":null},{"id":"2509.26601","title":"MENLO: From Preferences to Proficiency -- Evaluating and Modeling Native-like Quality Across 47 Languages","created":"2025-09-30","cited_by_count":3,"area":"alignment"},{"id":"2512.08786","title":"A Systematic Evaluation of Preference Aggregation in Federated RLHF for Pluralistic Alignment of LLMs","created":"2025-12-09","cited_by_count":3,"area":"alignment"},{"id":"2601.20838","title":"Reward Models Inherit Value Biases from Pretraining","created":"2026-01-28","cited_by_count":3,"area":"alignment"},{"id":"2603.02960","title":"Architecting Trust in Artificial Epistemic Agents","created":"2026-03-03","cited_by_count":3,"area":"agents"},{"id":"2503.08035","title":"Group Preference Alignment: Customized LLM Response Generation from In-Situ Conversations","created":"2025-03-11","cited_by_count":2,"area":"alignment"}],"next_cursor":"100"}