{"total":39,"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":"2508.17511","title":"School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs","created":"2025-08-24","cited_by_count":66,"area":"alignment"},{"id":"2506.19248","title":"Inference-Time Reward Hacking in Large Language Models","created":"2025-06-24","cited_by_count":34,"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":"2509.03403","title":"Beyond Correctness: Harmonizing Process and Outcome Rewards through RL Training","created":"2025-09-03","cited_by_count":29,"area":"alignment"},{"id":"2511.21654","title":"EvilGenie: A Reward Hacking Benchmark","created":"2025-11-26","cited_by_count":28,"area":"alignment"},{"id":"2603.07084","title":"Countdown-Code: A Testbed for Studying The Emergence and Generalization of Reward Hacking in RLVR","created":"2026-03-07","cited_by_count":17,"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":"2603.04069","title":"Monitoring Emergent Reward Hacking During Generation via Internal Activations","created":"2026-03-04","cited_by_count":14,"area":"alignment"},{"id":"2602.01750","title":"Adversarial Reward Auditing for Active Detection and Mitigation of Reward Hacking","created":"2026-02-02","cited_by_count":11,"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":"2505.13787","title":"Preference Learning with Lie Detectors can Induce Honesty or Evasion","created":"2025-05-20","cited_by_count":9,"area":"alignment"},{"id":"2601.03868","title":"What Matters For Safety Alignment?","created":"2026-01-07","cited_by_count":7,"area":"alignment"},{"id":"2602.19416","title":"IR$^3$: Contrastive Inverse Reinforcement Learning for Interpretable Detection and Mitigation of Reward Hacking","created":"2026-02-23","cited_by_count":5,"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":"2604.16242","title":"Detecting and Suppressing Reward Hacking with Gradient Fingerprints","created":"2026-04-17","cited_by_count":5,"area":"alignment"},{"id":"2606.24014","title":"Reinforcement Learning Towards Broadly and Persistently Beneficial Models","created":"2026-06-22","cited_by_count":4,"area":"alignment"},{"id":"2605.31328","title":"Reinforcement Learning Can Amplify Emergent Misalignment from Harmless Rewards","created":"2026-05-29","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":"2604.12086","title":"Robust Optimization for Mitigating Reward Hacking with Correlated Proxies","created":"2026-04-13","cited_by_count":2,"area":"alignment"},{"id":"2609.19101","title":"Monitoring and Discovering Reward Hacking with Internal Representations during LLM Evaluations","created":"2026-09-16","cited_by_count":2,"area":"alignment"},{"id":"2503.22480","title":"Probabilistic Uncertain Reward Model","created":"2025-03-28","cited_by_count":1,"area":"alignment"},{"id":"2511.17869","title":"The Horcrux: Mechanistically Interpretable Task Decomposition for Detecting and Mitigating Reward Hacking in Embodied AI Systems","created":"2025-11-22","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":"2606.09711","title":"Proxy Reward Internalization and Mechanistic Exploitation: A Learned Precursor to Reward Hacking and Its Generalization","created":"2026-06-08","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":"2607.28881","title":"Fragility of Value under Imperfect Alignment","created":"2026-07-30","cited_by_count":0,"area":"alignment"},{"id":"2608.22103","title":"Hack-Verifiable Terminal Bench: Evaluating Reward Hacking in Terminal Tasks","created":"2026-08-22","cited_by_count":0,"area":"alignment"},{"id":"2609.14998","title":"Shallow Beliefs: Synthetic document finetuning does not inoculate against emergent misalignment from reward hacking","created":"2026-09-14","cited_by_count":0,"area":"alignment"},{"id":"2609.35677","title":"Verifier Errors in RLVR: Reward Hacking, Limits of Feedback, and Selective Control","created":"2026-09-28","cited_by_count":0,"area":"alignment"},{"id":"2609.39533","title":"CATCH: A Controllable Analysis Testbed for Reward Hacking in Coding RL","created":"2026-09-30","cited_by_count":0,"area":"alignment"},{"id":"2610.03458","title":"A Near-Zero Monitor Readout Is Not Evidence of Behavioral Control","created":"2026-10-02","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"},{"id":"2610.17062","title":"Gradient Routing Localizes and Removes Unintended Behaviors in RL","created":"2026-10-12","cited_by_count":0,"area":"alignment"},{"id":"2610.19525","title":"Diagnosing and Correcting Reward Hacking in Verifiable Instruction Following","created":"2026-10-14","cited_by_count":0,"area":"alignment"},{"id":"2610.19832","title":"Rent-Seeking Language Models: Reward Models Set the Prices, Frequent Audits Curb the Rent","created":"2026-10-14","cited_by_count":0,"area":"alignment"}],"next_cursor":null}