{"total":51,"rows":[{"id":"2501.17420","title":"Actions Speak Louder than Words: Agent Decisions Reveal Implicit Biases in Language Models","created":"2025-01-29","cited_by_count":30,"area":"agents"},{"id":"2601.03746","title":"Whose Facts Win? LLM Source Preferences under Knowledge Conflicts","created":"2026-01-07","cited_by_count":12,"area":"rag"},{"id":"2505.21548","title":"Fluent but Foreign: Even Regional LLMs Lack Cultural Alignment","created":"2025-05-25","cited_by_count":10,"area":null},{"id":"2502.00313","title":"Distributive Fairness in Large Language Models: Evaluating Alignment with Human Values","created":"2025-02-01","cited_by_count":9,"area":"alignment"},{"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":"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":"2602.11328","title":"Evaluating Alignment of Behavioral Dispositions in LLMs","created":"2026-02-11","cited_by_count":7,"area":"alignment"},{"id":"2507.02197","title":"Do Role-Playing Agents Practice What They Preach? Belief-Behavior Consistency in LLM-Based Simulations of Human Trust","created":"2025-07-02","cited_by_count":6,"area":"agents"},{"id":"2511.02109","title":"Deep Value Benchmark: Measuring Whether Models Generalize Deep Values or Shallow Preferences","created":"2025-11-03","cited_by_count":6,"area":"alignment"},{"id":"2601.16356","title":"The Behavioral Fabric of LLM-Powered GUI Agents: Human Values and Interaction Outcomes","created":"2026-01-22","cited_by_count":4,"area":"agents"},{"id":"2602.08567","title":"ValueFlow: Measuring the Propagation of Value Perturbations in Multi-Agent LLM Systems","created":"2026-02-09","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":"2602.09416","title":"Are Language Models Sensitive to Morally Irrelevant Distractors?","created":"2026-02-10","cited_by_count":3,"area":null},{"id":"2608.05583","title":"The Judgment-Consequence Gap: LLM Moral Reasoning in Healthcare Decisions","created":"2026-08-06","cited_by_count":3,"area":null},{"id":"2608.21242","title":"Affective Context Amplifies Sycophancy in LLM Responses","created":"2026-08-21","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":"2509.10078","title":"Human Psychometric Questionnaires Mischaracterize LLM Behavior","created":"2025-09-12","cited_by_count":2,"area":null},{"id":"2511.12832","title":"From Passive to Persuasive: Localized Activation Injection for Empathy and Negotiation","created":"2025-11-16","cited_by_count":2,"area":"mechinterp"},{"id":"2511.21218","title":"Can Finetuing LLMs on Small Human Samples Increase Heterogeneity, Alignment, and Belief-Action Coherence?","created":"2025-11-26","cited_by_count":2,"area":null},{"id":"2604.08797","title":"Lessons Without Borders? Evaluating Cultural Alignment of LLMs Using Multilingual Story Moral Generation","created":"2026-04-09","cited_by_count":2,"area":null},{"id":"2605.12120","title":"To Whom Do Language Models Align? Measuring Principal Hierarchies Under High-Stakes Competing Demands","created":"2026-05-12","cited_by_count":2,"area":null},{"id":"2605.18738","title":"What Does the AI Doctor Value? Auditing Pluralism in the Clinical Ethics of Language Models","created":"2026-05-18","cited_by_count":2,"area":null},{"id":"2605.29791","title":"ActTraitBench: Quantifying the Knowledge-Decision Gap in Large Language Models via Human-Grounded Behavioral Validation","created":"2026-05-28","cited_by_count":2,"area":null},{"id":"2505.22981","title":"Free Lunch for User Experience: Crowdsourcing Agents for Scalable User Studies","created":"2025-05-29","cited_by_count":1,"area":"agents"},{"id":"2602.12134","title":"Value Alignment Tax: Measuring Value Trade-offs in LLM Alignment","created":"2026-02-12","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":"2604.07749","title":"Beyond Social Pressure: Benchmarking Epistemic Attack in Large Language Models","created":"2026-04-09","cited_by_count":1,"area":null},{"id":"2606.21939","title":"Beyond Value Benchmarks: Measuring Value-Structure Alignment in Large Language Models via Symmetric Q-Sorts","created":"2026-06-20","cited_by_count":1,"area":null},{"id":"2606.22974","title":"When Preferences Fail to Become Incentives: A Utility-Behavior Gap in Large Language Models","created":"2026-06-22","cited_by_count":1,"area":null},{"id":"2607.08034","title":"PLURAL: A Global Dataset for Value Alignment","created":"2026-07-09","cited_by_count":1,"area":"alignment"},{"id":"2608.07367","title":"People Are Not Just Their Countries. Disentangling Social Determinants of LLM Value Alignment Across Europe","created":"2026-08-07","cited_by_count":1,"area":null},{"id":"2608.23411","title":"STONIC: A Layered Measurement Contract for LLM Value Profiling","created":"2026-08-24","cited_by_count":1,"area":null},{"id":"2608.26178","title":"AI Revealed Preferences","created":"2026-08-17","cited_by_count":1,"area":"alignment"},{"id":"2503.00992","title":"Evidence of conceptual mastery in the application of rules by Large Language Models","created":"2025-03-02","cited_by_count":0,"area":null},{"id":"2505.17413","title":"Conversations: Love Them, Hate Them, Steer Them","created":"2025-05-23","cited_by_count":0,"area":null},{"id":"2512.10172","title":"Offscript: Automated Auditing of Instruction Adherence in LLMs","created":"2025-12-11","cited_by_count":0,"area":null},{"id":"2512.21551","title":"Human-AI Interaction Alignment: Designing, Evaluating, and Evolving Value-Centered AI For Reciprocal Human-AI Futures","created":"2025-12-25","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":"2602.11091","title":"Can Large Language Models Make Everyone Happy?","created":"2026-02-11","cited_by_count":0,"area":null},{"id":"2602.11305","title":"Are Aligned Large Language Models Still Misaligned?","created":"2026-02-11","cited_by_count":0,"area":"alignment"},{"id":"2602.17283","title":"Towards Cross-lingual Values Judgment: A Consensus-Pluralism Perspective","created":"2026-02-19","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":"2607.20270","title":"Which Values Do LLMs Confuse? A Schwartz-Based Recognition Study","created":"2026-07-22","cited_by_count":0,"area":null},{"id":"2607.21279","title":"A Unified Moral-Value Dataset for Instruction Tuning","created":"2026-07-23","cited_by_count":0,"area":null},{"id":"2608.20355","title":"ExpertIVS: Sociological Expert Driven Individual Value Simulation in Large Language Models","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2609.05514","title":"The Failure Happens Before the Drift: The Social Dynamics of Values in LLM Agent Societies","created":"2026-08-31","cited_by_count":0,"area":"agents"},{"id":"2609.22494","title":"CultureMINE: Datasets and Methods for Improving the Cultural Capabilities of NLP Systems","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2609.32638","title":"Can Open-Weight Large Language Models (LLMs) Simulate Human Survey Populations? A Cross-Instrument Calibration Study","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.32776","title":"On the Behavioral Traits of LLM Agents","created":"2026-09-26","cited_by_count":0,"area":"agents"},{"id":"2610.02622","title":"CuBEs: Culturally-Situated Behavioral Evaluations and the Limitations of Culture-Blind LLM Judges","created":"2026-10-02","cited_by_count":0,"area":"wm"},{"id":"2610.08670","title":"Principled Under Pressure: Post-Training Decides Whether LLMs Act on Their Own Moral Judgment","created":"2026-10-06","cited_by_count":0,"area":null}],"next_cursor":null}