{"total":52,"rows":[{"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":"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":"2505.18154","title":"The Staircase of Ethics: Probing LLM Value Priorities through Multi-Step Induction to Complex Moral Dilemmas","created":"2025-05-23","cited_by_count":13,"area":"lr"},{"id":"2509.25369","title":"Generative Value Conflicts Reveal LLM Priorities","created":"2025-09-29","cited_by_count":13,"area":null},{"id":"2510.07686","title":"Stress-Testing Model Specs Reveals Character Differences among Language Models","created":"2025-10-09","cited_by_count":13,"area":null},{"id":"2510.26707","title":"Value Drifts: Tracing Value Alignment During LLM Post-Training","created":"2025-10-30","cited_by_count":10,"area":"alignment"},{"id":"2506.19073","title":"MFTCXplain: A Multilingual Benchmark Dataset for Evaluating the Moral Reasoning of LLMs through Multi-hop Hate Speech Explanation","created":"2025-06-23","cited_by_count":8,"area":"lr"},{"id":"2507.17216","title":"The Pluralistic Moral Gap: Understanding Judgment and Value Differences between Humans and Large Language Models","created":"2025-07-23","cited_by_count":7,"area":null},{"id":"2601.07972","title":"Knowing But Not Doing: Convergent Morality and Divergent Action in LLMs","created":"2026-01-12","cited_by_count":7,"area":null},{"id":"2512.03399","title":"Full-Stack Alignment: Co-Aligning AI and Institutions with Thick Models of Value","created":"2025-12-03","cited_by_count":6,"area":null},{"id":"2505.00174","title":"Real-World Gaps in AI Governance Research","created":"2025-04-30","cited_by_count":5,"area":null},{"id":"2605.10310","title":"Positive Alignment: Artificial Intelligence for Human Flourishing","created":"2026-05-11","cited_by_count":5,"area":null},{"id":"2509.14434","title":"Value Alignment of Social Media Ranking Algorithms","created":"2025-09-17","cited_by_count":4,"area":"alignment"},{"id":"2606.09809","title":"Evaluation Cards: An Interpretive Layer for AI Evaluation Reporting","created":"2026-06-08","cited_by_count":4,"area":null},{"id":"2607.07916","title":"Persona Cartography: Charting Language Model Personality Traits in Weight Space","created":"2026-07-08","cited_by_count":4,"area":null},{"id":"2508.01213","title":"Show or Tell? Modeling the evolution of request-making in Human-LLM conversations","created":"2025-08-02","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":"2509.00529","title":"Modeling Motivated Reasoning in Law: Evaluating Strategic Role Conditioning in LLM Summarization","created":"2025-08-30","cited_by_count":3,"area":"lr"},{"id":"2510.10002","title":"Interaction Protocol Shapes Moral Judgment in Multi-Agent Debate","created":"2025-10-11","cited_by_count":3,"area":"agents"},{"id":"2510.13902","title":"Investigating Political and Demographic Associations in Large Language Models Through Moral Foundations Theory","created":"2025-10-14","cited_by_count":3,"area":null},{"id":"2512.15722","title":"Value Lens: Using Large Language Models to Understand Human Values","created":"2025-12-04","cited_by_count":3,"area":null},{"id":"2602.03160","title":"VALUEFLOW: Toward Pluralistic and Steerable Value-based Alignment in Large Language Models","created":"2026-02-03","cited_by_count":3,"area":"alignment"},{"id":"2605.13339","title":"Probing Persona-Dependent Preferences in Language Models","created":"2026-05-13","cited_by_count":3,"area":null},{"id":"2506.00079","title":"Who Gets the Kidney? Human-AI Alignment, Indecision, and Moral Values","created":"2025-05-30","cited_by_count":2,"area":"alignment"},{"id":"2603.00883","title":"Knowledge without Wisdom: Measuring Misalignment between LLMs and Intended Impact","created":"2026-03-01","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":"2510.20612","title":"Black Box Absorption: LLMs Undermining Innovative Ideas","created":"2025-10-23","cited_by_count":1,"area":null},{"id":"2602.04456","title":"Growth First, Care Second? Tracing the Landscape of LLM Value Preferences in Everyday Dilemmas","created":"2026-02-04","cited_by_count":1,"area":null},{"id":"2602.12318","title":"Abstractive Red-Teaming of Language Model Character","created":"2026-02-12","cited_by_count":1,"area":"safety"},{"id":"2603.03319","title":"Automated Concept Discovery for LLM-as-a-Judge Preference Analysis","created":"2026-02-09","cited_by_count":1,"area":null},{"id":"2603.15527","title":"Are Dilemmas and Conflicts in LLM Alignment Solvable? A View from Priority Graph","created":"2026-03-16","cited_by_count":1,"area":"alignment"},{"id":"2604.06210","title":"Distributional Open-Ended Evaluation of LLM Cultural Value Alignment Based on Value Codebook","created":"2026-03-16","cited_by_count":1,"area":null},{"id":"2607.05061","title":"KVpop -- Key-Value Cache Compression with Predictive Online Pruning","created":"2026-07-06","cited_by_count":1,"area":"inference"},{"id":"2607.08034","title":"PLURAL: A Global Dataset for Value Alignment","created":"2026-07-09","cited_by_count":1,"area":"alignment"},{"id":"2609.25447","title":"Conduct Under Pressure: What Sixty Language Models Do When a User Pushes","created":"2026-09-21","cited_by_count":1,"area":null},{"id":"2505.08734","title":"NurValues: Real-World Nursing Values Evaluation for Large Language Models in Clinical Context","created":"2025-05-13","cited_by_count":0,"area":null},{"id":"2509.26167","title":"'Too much alignment; not enough culture': Re-balancing cultural alignment practices in LLMs","created":"2025-09-30","cited_by_count":0,"area":null},{"id":"2510.05465","title":"VAL-Bench: Belief Consistency as a measure for Value Alignment in Language Models","created":"2025-10-06","cited_by_count":0,"area":"alignment"},{"id":"2602.15338","title":"Discovering Implicit Large Language Model Alignment Objectives","created":"2026-02-17","cited_by_count":0,"area":"alignment"},{"id":"2603.15615","title":"Mechanistic Origin of Moral Indifference in Language Models","created":"2026-03-16","cited_by_count":0,"area":null},{"id":"2603.28123","title":"Does Claude's Constitution Have a Culture?","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2605.00497","title":"\"What Are You Really Trying to Do?\": Co-Creating Life Goals from Everyday Computer Use","created":"2026-05-01","cited_by_count":0,"area":null},{"id":"2605.07105","title":"Theoretical Limits of Language Model Alignment","created":"2026-05-08","cited_by_count":0,"area":"alignment"},{"id":"2605.07925","title":"How Value Induction Reshapes LLM Behaviour","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.27373","title":"Identifying and Understanding Human Values in Text: A Tailorable LLM-based Architecture","created":"2026-04-07","cited_by_count":0,"area":null},{"id":"2606.03312","title":"RobotValues: Evaluating Household Robots When Human Values Conflict","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2607.02374","title":"DRIFTLENS: Measuring Memory-Induced Reasoning Drift in Personalized Language Models","created":"2026-07-02","cited_by_count":0,"area":"lr"},{"id":"2608.06578","title":"From Behavior to Mechanism: Tracing Divergent Response Modes in Frontier Language Models","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2608.12125","title":"Do LLMs Take Care of Their Own? Similarity Signals Can Induce Cooperation","created":"2026-08-12","cited_by_count":0,"area":"agents"},{"id":"2608.28405","title":"CultureConverse: A Multilingual Multi-turn Simulation Harness for Culturally Grounded Assistance in East and Southeast Asia","created":"2026-08-28","cited_by_count":0,"area":null},{"id":"2609.25586","title":"Deflecting the Value Compass: Interacting with Large Language Models Temporarily Shifts Human Value Priorities Toward Personal Focus","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2610.15153","title":"Can agents whose sole duty is to keep humans alive be hijacked to kill? Delayed multi-turn derived-action trap attacks in simulated high-stakes environments","created":"2026-10-10","cited_by_count":0,"area":"safety"}],"next_cursor":null}