{"total":34,"rows":[{"id":"2511.18397","title":"Natural Emergent Misalignment from Reward Hacking in Production RL","created":"2025-11-23","cited_by_count":136,"area":"alignment"},{"id":"2604.13602","title":"Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges","created":"2026-04-15","cited_by_count":33,"area":"alignment"},{"id":"2506.09996","title":"From Judgment to Interference: Early Stopping LLM Harmful Outputs via Streaming Content Monitoring","created":"2025-06-11","cited_by_count":22,"area":"alignment"},{"id":"2503.02574","title":"LLM-Safety Evaluations Lack Robustness","created":"2025-03-04","cited_by_count":18,"area":"alignment"},{"id":"2507.19672","title":"Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges","created":"2025-07-25","cited_by_count":15,"area":"alignment"},{"id":"2508.06249","title":"In-Training Defenses against Emergent Misalignment in Language Models","created":"2025-08-08","cited_by_count":15,"area":"alignment"},{"id":"2510.26707","title":"Value Drifts: Tracing Value Alignment During LLM Post-Training","created":"2025-10-30","cited_by_count":10,"area":"alignment"},{"id":"2605.20744","title":"Hack-Verifiable Environments: Towards Evaluating Reward Hacking at Scale","created":"2026-05-20","cited_by_count":10,"area":"alignment"},{"id":"2503.00069","title":"Societal Alignment Frameworks Can Improve LLM Alignment","created":"2025-02-27","cited_by_count":8,"area":"alignment"},{"id":"2503.06646","title":"Evaluating and Aligning Human Economic Risk Preferences in LLMs","created":"2025-03-09","cited_by_count":8,"area":"alignment"},{"id":"2506.13901","title":"Alignment Quality Index (AQI) : Beyond Refusals: AQI as an Intrinsic Alignment Diagnostic via Latent Geometry, Cluster Divergence, and Layer wise Pooled Representations","created":"2025-06-16","cited_by_count":8,"area":"alignment"},{"id":"2604.01476","title":"From Rebound to Remedy: Understanding and Mitigating Reward Hacking via Representation Engineering","created":"2026-04-01","cited_by_count":7,"area":"alignment"},{"id":"2510.19050","title":"Rectifying Shortcut Behaviors in Preference-based Reward Learning","created":"2025-10-21","cited_by_count":6,"area":"alignment"},{"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":"2602.14777","title":"Emergently Misaligned Language Models Show Behavioral Self-Awareness That Shifts With Subsequent Realignment","created":"2026-02-16","cited_by_count":6,"area":"alignment"},{"id":"2604.13051","title":"The Consciousness Cluster: Emergent preferences of Models that Claim to be Conscious","created":"2026-03-17","cited_by_count":5,"area":"alignment"},{"id":"2603.01204","title":"Subliminal Signals in Preference Labels","created":"2026-03-01","cited_by_count":3,"area":"alignment"},{"id":"2607.18966","title":"Measuring Reward-Seeking via Contrastive Belief Updates","created":"2026-07-21","cited_by_count":3,"area":"alignment"},{"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":"2510.01266","title":"OpenAI's GPT-OSS-20B Model and Safety Alignment Issues in a Low-Resource Language","created":"2025-09-26","cited_by_count":1,"area":"alignment"},{"id":"2602.16987","title":"A testable framework for AI alignment: Simulation Theology as an engineered worldview for silicon-based agents","created":"2026-02-19","cited_by_count":1,"area":"alignment"},{"id":"2604.26511","title":"Tatemae: Detecting Alignment Faking via Tool Selection in LLMs","created":"2026-04-29","cited_by_count":1,"area":"alignment"},{"id":"2606.12016","title":"Generalization Hacking: Models Can Game Reinforcement Learning by Preventing Behavioral Generalization","created":"2026-06-10","cited_by_count":1,"area":"alignment"},{"id":"2610.10947","title":"RH-Detect: A Unified Benchmark for Reward Hacking Detection","created":"2026-10-07","cited_by_count":1,"area":"alignment"},{"id":"2508.06592","title":"Towards Integrated Alignment","created":"2025-08-08","cited_by_count":0,"area":"alignment"},{"id":"2605.20994","title":"Towards Context-Invariant Safety Alignment for Large Language Models","created":"2026-05-20","cited_by_count":0,"area":"alignment"},{"id":"2605.27355","title":"Alignment Tampering: How Reinforcement Learning from Human Feedback Is Exploited to Optimize Misaligned Biases","created":"2026-05-26","cited_by_count":0,"area":"alignment"},{"id":"2606.19527","title":"Emergent Alignment","created":"2026-06-17","cited_by_count":0,"area":"alignment"},{"id":"2609.05009","title":"Language models judge war differently when tested for alignment","created":"2026-09-04","cited_by_count":0,"area":"alignment"},{"id":"2609.06934","title":"The Geometry of Refusal: Why Post-Hoc Safety Is Fragile and Pretraining-Time Safety Persists","created":"2026-09-07","cited_by_count":0,"area":"alignment"},{"id":"2609.38645","title":"Alignment via Training Against Probes Without Losing Monitorability","created":"2026-09-29","cited_by_count":0,"area":"alignment"},{"id":"2610.04793","title":"Pressure, Context, and Machine Self-Control: A Criminological Test of Reward Hacking in Generative AI Models","created":"2026-10-03","cited_by_count":0,"area":"alignment"},{"id":"2610.07935","title":"SIGMA: Self-Improving Alignment Generalization from a Model Spec","created":"2026-10-06","cited_by_count":0,"area":"alignment"},{"id":"2610.12822","title":"Reward Hacking as a Transmissible Strategy in Multi-Agent Coding Systems","created":"2026-10-09","cited_by_count":0,"area":"alignment"}],"next_cursor":null}