{"total":67,"rows":[{"id":"2502.17424","title":"Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs","created":"2025-02-24","cited_by_count":172,"area":"safety"},{"id":"2503.03750","title":"The MASK Benchmark: Disentangling Honesty From Accuracy in AI Systems","created":"2025-03-05","cited_by_count":72,"area":"agents"},{"id":"2506.13206","title":"Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models","created":"2025-06-16","cited_by_count":65,"area":"lr"},{"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":"2508.05687","title":"Risk Analysis Techniques for Governed LLM-based Multi-Agent Systems","created":"2025-08-06","cited_by_count":18,"area":"agents"},{"id":"2509.01063","title":"An Economy of AI Agents","created":"2025-09-01","cited_by_count":18,"area":null},{"id":"2604.17596","title":"Terminal Wrench: A Dataset of 331 Reward-Hackable Environments and 3,632 Exploit Trajectories","created":"2026-04-19","cited_by_count":15,"area":null},{"id":"2509.25369","title":"Generative Value Conflicts Reveal LLM Priorities","created":"2025-09-29","cited_by_count":13,"area":null},{"id":"2505.21479","title":"Are Language Models Consequentialist or Deontological Moral Reasoners?","created":"2025-05-27","cited_by_count":12,"area":"lr"},{"id":"2503.18825","title":"EconEvals: Benchmarks and Litmus Tests for Economic Decision-Making by LLM Agents","created":"2025-03-24","cited_by_count":10,"area":"agents"},{"id":"2506.20702","title":"The Singapore Consensus on Global AI Safety Research Priorities","created":"2025-06-25","cited_by_count":10,"area":null},{"id":"2507.17951","title":"Are LLM Belief Updates Consistent with Bayes' Theorem?","created":"2025-07-23","cited_by_count":9,"area":null},{"id":"2503.05628","title":"Superintelligence Strategy: Expert Version","created":"2025-03-07","cited_by_count":7,"area":null},{"id":"2602.18971","title":"When Do LLM Preferences Predict Downstream Behavior?","created":"2026-02-21","cited_by_count":7,"area":"alignment"},{"id":"2505.11615","title":"Steering Risk Preferences in Large Language Models by Aligning Behavioral and Neural Representations","created":"2025-05-16","cited_by_count":6,"area":"mechinterp"},{"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":"2508.20015","title":"Decomposing Behavioral Phase Transitions in LLMs: Order Parameters for Emergent Misalignment","created":"2025-08-27","cited_by_count":5,"area":null},{"id":"2603.10028","title":"How to Count AIs: Individuation and Liability for AI Agents","created":"2026-02-24","cited_by_count":5,"area":null},{"id":"2605.08556","title":"Can Revealed Preferences Clarify LLM Alignment and Steering?","created":"2026-05-08","cited_by_count":5,"area":"alignment"},{"id":"2503.05830","title":"AI-Enhanced Deliberative Democracy and the Future of the Collective Will","created":"2025-03-06","cited_by_count":4,"area":null},{"id":"2505.24539","title":"Localizing Persona Representations in LLMs","created":"2025-05-30","cited_by_count":3,"area":null},{"id":"2605.13339","title":"Probing Persona-Dependent Preferences in Language Models","created":"2026-05-13","cited_by_count":3,"area":null},{"id":"2608.05015","title":"Revealed Rationality: Label-Free Evaluation and Regularization from Representation Theorems","created":"2026-08-05","cited_by_count":3,"area":null},{"id":"2509.01938","title":"EigenBench: A Comparative Behavioral Measure of Value Alignment","created":"2025-09-02","cited_by_count":2,"area":"alignment"},{"id":"2509.17192","title":"Shall We Play a Game? Language Models for Open-ended Wargames","created":"2025-09-21","cited_by_count":2,"area":null},{"id":"2512.11986","title":"Learning to Extract Context for Context-Aware LLM Inference","created":"2025-12-12","cited_by_count":2,"area":null},{"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":"2606.13944","title":"LLMs Contain Multitudes: How Deployment Context Reshapes Model-Level Preferences and Values","created":"2026-06-11","cited_by_count":2,"area":null},{"id":"2606.21102","title":"Incoherent Values? Probing LLM Preferences Through Parametric Variation","created":"2026-06-19","cited_by_count":2,"area":"alignment"},{"id":"2607.02047","title":"OpenSafeIntent: Evaluating Intent-Calibrated Safe Completion Across Dual-Use Prompt Sets","created":"2026-07-02","cited_by_count":2,"area":null},{"id":"2609.01595","title":"Mechanism Design for Alignment and Control","created":"2026-09-01","cited_by_count":2,"area":null},{"id":"2503.07660","title":"Research Superalignment Should Advance Now with Alternating Competence and Conformity Optimization","created":"2025-03-08","cited_by_count":1,"area":"alignment"},{"id":"2504.15125","title":"Contemplative Artificial Intelligence","created":"2025-04-21","cited_by_count":1,"area":null},{"id":"2602.08964","title":"A Behavioural and Representational Evaluation of Goal-Directedness in Language Model Agents","created":"2026-02-09","cited_by_count":1,"area":"agents"},{"id":"2602.19101","title":"Value Entanglement: Conflation Between Different Kinds of Good In (Some) Large Language Models","created":"2026-02-22","cited_by_count":1,"area":"alignment"},{"id":"2603.21006","title":"How AI Systems Think About Education: Analyzing Latent Preference Patterns in Large Language Models","created":"2026-02-28","cited_by_count":1,"area":"lr"},{"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":"2607.02755","title":"Out-of-Distribution Generalization of Risk Aversion in Language Models","created":"2026-07-02","cited_by_count":1,"area":null},{"id":"2607.19367","title":"Rethinking Uncertainty Evaluation in Large Language Models","created":"2026-06-11","cited_by_count":1,"area":"lr"},{"id":"2608.01361","title":"High-Stakes Decisions with Language Models: Insights from Emergency Triage","created":"2026-08-02","cited_by_count":1,"area":null},{"id":"2608.26178","title":"AI Revealed Preferences","created":"2026-08-17","cited_by_count":1,"area":"alignment"},{"id":"2503.13554","title":"LLMs' Leaning in European Elections","created":"2025-03-16","cited_by_count":0,"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":"2507.05187","title":"Infrastructuring Contestability: A Framework for Community-Defined AI Value Pluralism","created":"2025-07-07","cited_by_count":0,"area":null},{"id":"2510.15395","title":"Corrigibility Transformation: Constructing Goals That Accept Updates","created":"2025-10-17","cited_by_count":0,"area":null},{"id":"2601.07473","title":"AntiPaSTO: Self-Supervised Honesty Steering via Anti-Parallel Representations","created":"2026-01-12","cited_by_count":0,"area":null},{"id":"2602.10964","title":"Can LLMs Cook Jamaican Couscous? A Study of Cultural Novelty in Recipe Generation","created":"2026-02-11","cited_by_count":0,"area":null},{"id":"2602.18459","title":"From Bias Mitigation to Bias Negotiation: Governing Identity and Sociocultural Reasoning in Generative AI","created":"2026-02-05","cited_by_count":0,"area":"lr"},{"id":"2603.03295","title":"Language Model Goal Selection Differs from Humans' in a Self-Directed Learning Task","created":"2026-02-06","cited_by_count":0,"area":"agents"},{"id":"2603.14417","title":"Questionnaire Responses Do not Capture the Safety of AI Agents","created":"2026-03-15","cited_by_count":0,"area":"agents"},{"id":"2605.22771","title":"Reducing Political Manipulation with Consistency Training","created":"2026-05-21","cited_by_count":0,"area":null},{"id":"2605.23565","title":"Understanding Goal Generalisation in Sequential Reinforcement Learning","created":"2026-05-22","cited_by_count":0,"area":"deeprl"},{"id":"2606.11016","title":"Superficial Beliefs in LLM Decision-Making","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2607.18548","title":"Engineering Trustworthy Agentic AI for Critical Systems","created":"2026-07-20","cited_by_count":0,"area":"agents"},{"id":"2608.00339","title":"Bayesian and Motivated Reasoning in AI Agents","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2608.10327","title":"Toward a Theory of Value in AI Alignment","created":"2026-08-10","cited_by_count":0,"area":"alignment"},{"id":"2608.23641","title":"How much of a measured AI preference is the model, and how much is the instrument?","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2609.00304","title":"The Assistant's Ideal Self","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.05036","title":"Moral Competence Before Moral Content: Why LLM Agents Lack the Prerequisites for Coherent Alignment","created":"2026-09-04","cited_by_count":0,"area":"agents"},{"id":"2609.09899","title":"Strangers to Themselves: What Language Models Say About Themselves Is Generic","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.14724","title":"Bayesian Intelligence from the Outside","created":"2026-09-13","cited_by_count":0,"area":null},{"id":"2609.16667","title":"ANIMASK: What the Model Contributes to Role Play in Simulated Story Worlds","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2609.20408","title":"Xeno-Interpretability: Investigating the Alien Minds of LLMs","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.22170","title":"Multiple latent orderings better predict language model preferences","created":"2026-08-26","cited_by_count":0,"area":"alignment"},{"id":"2609.35591","title":"Language Models Act on Hidden Valence","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.00767","title":"Pre-training interventions, ex post facto: Grafting model beliefs across checkpoints","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.09164","title":"Training Language Models To Be Coherent Decision-Makers","created":"2026-10-06","cited_by_count":0,"area":null}],"next_cursor":null}