{"total":59,"rows":[{"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":"2504.15236","title":"Values in the Wild: Discovering and Analyzing Values in Real-World Language Model Interactions","created":"2025-04-21","cited_by_count":52,"area":null},{"id":"2502.08045","title":"Break the Checkbox: Challenging Closed-Style Evaluations of Cultural Alignment in LLMs","created":"2025-02-12","cited_by_count":26,"area":null},{"id":"2506.12657","title":"Synthetic Socratic Debates: Examining Persona Effects on Moral Decision and Persuasion Dynamics","created":"2025-06-14","cited_by_count":19,"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":"2505.18154","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":"2504.10823","title":"CLASH: Evaluating Language Models on Judging High-Stakes Dilemmas from Multiple Perspectives","created":"2025-04-15","cited_by_count":10,"area":null},{"id":"2506.13082","title":"Discerning What Matters: A Multi-Dimensional Assessment of Moral Competence in LLMs","created":"2025-06-16","cited_by_count":10,"area":null},{"id":"2412.20718","title":"MM-MoralBench: A MultiModal Moral Evaluation Benchmark for Large Vision-Language Models","created":"2024-12-30","cited_by_count":9,"area":"mllm"},{"id":"2506.23678","title":"Interactive Reasoning: Visualizing and Controlling Chain-of-Thought Reasoning in Large Language Models","created":"2025-06-30","cited_by_count":9,"area":"lr"},{"id":"2510.11254","title":"Do Psychometric Tests Work for Large Language Models? Evaluation of Tests on Sexism, Racism, and Morality","created":"2025-10-13","cited_by_count":9,"area":null},{"id":"2603.05651","title":"The Fragility Of Moral Judgment In Large Language Models","created":"2026-03-05","cited_by_count":8,"area":null},{"id":"2511.12014","title":"CURE: Cultural Understanding and Reasoning Evaluation - A Framework for \"Thick\" Culture Alignment Evaluation in LLMs","created":"2025-11-15","cited_by_count":7,"area":"lr"},{"id":"2510.05942","title":"EvalMORAAL: Interpretable Chain-of-Thought and LLM-as-Judge Evaluation for Moral Alignment in Large Language Models","created":"2025-10-07","cited_by_count":6,"area":"lr"},{"id":"2506.09656","title":"Multi-level Value Alignment in Agentic AI Systems: Survey and Perspectives","created":"2025-06-11","cited_by_count":5,"area":"agents"},{"id":"2506.22957","title":"Agent-to-Agent Theory of Mind: Testing Interlocutor Awareness among Large Language Models","created":"2025-06-28","cited_by_count":5,"area":"agents"},{"id":"2510.18526","title":"Counterfactual Reasoning for Steerable Pluralistic Value Alignment of Large Language Models","created":"2025-10-21","cited_by_count":5,"area":"lr"},{"id":"2605.10310","title":"Positive Alignment: Artificial Intelligence for Human Flourishing","created":"2026-05-11","cited_by_count":5,"area":null},{"id":"2509.25897","title":"RoleConflictBench: A Benchmark of Role Conflict Scenarios for Evaluating LLMs' Contextual Sensitivity","created":"2025-09-30","cited_by_count":4,"area":null},{"id":"2603.03456","title":"Asymmetric Goal Drift in Coding Agents Under Value Conflict","created":"2026-03-03","cited_by_count":4,"area":"agents"},{"id":"2604.05339","title":"Human Values Matter: Investigating How Misalignment Shapes Collective Behaviors in LLM Agent Communities","created":"2026-04-07","cited_by_count":4,"area":"agents"},{"id":"2604.12479","title":"Meet Dynamic Individual Preferences: Resolving Conflicting Human Value with Paired Fine-Tuning","created":"2026-04-14","cited_by_count":4,"area":"alignment"},{"id":"2510.06370","title":"EVALUESTEER: Measuring Reward Model Steerability Towards Values and Preferences","created":"2025-10-07","cited_by_count":3,"area":"alignment"},{"id":"2510.10002","title":"Interaction Protocol Shapes Moral Judgment in Multi-Agent Debate","created":"2025-10-11","cited_by_count":3,"area":"agents"},{"id":"2601.22396","title":"Culturally Grounded Personas in Large Language Models: Characterization and Alignment with Socio-Psychological Value Frameworks","created":"2026-01-29","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":"2604.20995","title":"Value-Conflict Diagnostics Reveal Widespread Alignment Faking in Language Models","created":"2026-04-22","cited_by_count":3,"area":null},{"id":"2505.09938","title":"Design and Evaluation of Generative Agent-based Platform for Human-Assistant Interaction Research: A Tale of 10 User Studies","created":"2025-05-15","cited_by_count":2,"area":"agents"},{"id":"2506.02481","title":"Do Language Models Think Consistently? A Study of Value Preferences Across Varying Response Lengths","created":"2025-06-03","cited_by_count":2,"area":"lr"},{"id":"2606.21102","title":"Incoherent Values? Probing LLM Preferences Through Parametric Variation","created":"2026-06-19","cited_by_count":2,"area":"alignment"},{"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":"2602.16438","title":"Intra-Fairness Dynamics: The Bias Spillover Effect in Targeted LLM Alignment","created":"2026-02-18","cited_by_count":1,"area":"alignment"},{"id":"2603.09434","title":"Common Sense vs. Morality: The Curious Case of Narrative Focus Bias in LLMs","created":"2026-03-10","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":"2607.16232","title":"From Weights to Words: Expressing and Editing Preference Model Inferences in Natural Language","created":"2026-06-24","cited_by_count":1,"area":null},{"id":"2607.19834","title":"D2VBench: Benchmarking Large Language Models with Value Dilemmas in Daily Scenarios","created":"2026-07-22","cited_by_count":1,"area":null},{"id":"2608.18081","title":"Position: Behavioral Systems Require Behavioral Tests","created":"2026-05-31","cited_by_count":1,"area":"agents"},{"id":"2608.23411","title":"STONIC: A Layered Measurement Contract for LLM Value Profiling","created":"2026-08-24","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":"2509.23698","title":"VIVA+: Human-Centered Situational Decision-Making","created":"2025-09-28","cited_by_count":0,"area":"mllm"},{"id":"2511.02623","title":"The Realignment Problem: When Right becomes Wrong in LLMs","created":"2025-11-04","cited_by_count":0,"area":"alignment"},{"id":"2601.03546","title":"Value-Action Alignment in Large Language Models under Privacy-Prosocial Conflict","created":"2026-01-07","cited_by_count":0,"area":null},{"id":"2605.03609","title":"Where Paths Split: Localized, Calibrated Control of Moral Reasoning in Large Language Models","created":"2026-05-05","cited_by_count":0,"area":"lr"},{"id":"2606.02214","title":"Do Gender Cues Affect LLM Value Trade-offs? Evidence from a Controlled Decision Benchmark","created":"2026-06-01","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":"2606.11016","title":"Superficial Beliefs in LLM Decision-Making","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2606.26366","title":"Narration-of-Thought: Inference-Time Scaffolding for Defeasible Ethical Reasoning in Large Language Models","created":"2026-06-24","cited_by_count":0,"area":"lr"},{"id":"2606.31213","title":"Can LLMs Imagine Moral Alternatives Beyond Binary Dilemmas?","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2606.31644","title":"Moral Safety in LLMs: Exposing Performative Compliance with Puzzled Cues","created":"2026-06-30","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":"2607.10202","title":"When Counterbalancing Hides the Bias: Access-Conditioned Position Lock in Forced-Choice LLM Evaluation","created":"2026-07-11","cited_by_count":0,"area":null},{"id":"2607.11736","title":"MET: Theory-Grounded and Culture-Aware Multilingual Moral Reasoning","created":"2026-07-13","cited_by_count":0,"area":"lr"},{"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":"2609.18384","title":"GYROval: A Robust Benchmark for Cultural Value Orientation in Large Language Models","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.28942","title":"From Static Personal Values to Contextualized Personalization: Bayesian Personalized Value Alignment for LLMs","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2610.10594","title":"Coverage, Not Difficulty, Sets How Much Synthetic Data an Activation Probe Needs","created":"2026-10-06","cited_by_count":0,"area":"synth"}],"next_cursor":null}