{"total":66,"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":"2510.04340","title":"Inoculation Prompting: Eliciting traits from LLMs during training can suppress them at test-time","created":"2025-10-05","cited_by_count":43,"area":null},{"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":"2605.02964","title":"Reward Hacking Benchmark: Measuring Exploits in LLM Agents with Tool Use","created":"2026-05-03","cited_by_count":31,"area":"agents"},{"id":"2601.20103","title":"Benchmarking Reward Hack Detection in Code Environments via Contrastive Analysis","created":"2026-01-27","cited_by_count":18,"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":"2604.25891","title":"Conditional misalignment: common interventions can hide emergent misalignment behind contextual triggers","created":"2026-04-28","cited_by_count":17,"area":null},{"id":"2512.19027","title":"Recontextualization Mitigates Specification Gaming without Modifying the Specification","created":"2025-12-22","cited_by_count":14,"area":null},{"id":"2603.04069","title":"Monitoring Emergent Reward Hacking During Generation via Internal Activations","created":"2026-03-04","cited_by_count":14,"area":"alignment"},{"id":"2602.11524","title":"Adaptive Milestone Reward for GUI Agents","created":"2026-02-12","cited_by_count":12,"area":"agents"},{"id":"2602.15515","title":"The Obfuscation Atlas: Mapping Where Honesty Emerges in RLVR with Deception Probes","created":"2026-02-17","cited_by_count":12,"area":null},{"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":"2606.08960","title":"Hardening Agent Benchmarks with Adversarial Hacker-Fixer Loops","created":"2026-06-08","cited_by_count":9,"area":"agents"},{"id":"2510.08211","title":"LLMs Deceive Unintentionally: Emergent Misalignment in Dishonesty from Misaligned Samples to Biased Human-AI Interactions","created":"2025-10-09","cited_by_count":8,"area":null},{"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":"2605.00842","title":"Understanding Emergent Misalignment via Feature Superposition Geometry","created":"2026-04-07","cited_by_count":7,"area":"mechinterp"},{"id":"2601.15220","title":"Privacy Collapse: Benign Fine-Tuning Can Break Contextual Privacy in Language Models","created":"2026-01-21","cited_by_count":6,"area":null},{"id":"2603.25681","title":"Self-Improvement of Large Language Models: A Technical Overview and Future Outlook","created":"2026-03-26","cited_by_count":5,"area":"synth"},{"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":"2606.24014","title":"Reinforcement Learning Towards Broadly and Persistently Beneficial Models","created":"2026-06-22","cited_by_count":4,"area":"alignment"},{"id":"2604.11072","title":"Hodoscope: Unsupervised Monitoring for AI Misbehaviors","created":"2026-04-13","cited_by_count":3,"area":null},{"id":"2605.02269","title":"Towards Understanding Specification Gaming in Reasoning Models","created":"2026-05-04","cited_by_count":3,"area":"lr"},{"id":"2605.31328","title":"Reinforcement Learning Can Amplify Emergent Misalignment from Harmless Rewards","created":"2026-05-29","cited_by_count":3,"area":"alignment"},{"id":"2606.06223","title":"From Reward-Hack Activations to Agentic Risk States: Context-Calibrated Mechanistic Monitoring in LLM Agents","created":"2026-06-04","cited_by_count":3,"area":"agents"},{"id":"2606.30252","title":"Inoculation Adapters: Improved Selective Generalization of Capabilities with Fewer Surprising Backdoors","created":"2026-06-29","cited_by_count":3,"area":null},{"id":"2607.21356","title":"Emergent Misalignment Recruits a Pre-existing Persona Subspace","created":"2026-07-23","cited_by_count":3,"area":"alignment"},{"id":"2510.14381","title":"Are My Optimized Prompts Compromised? Exploring Vulnerabilities of LLM-based Optimizers","created":"2025-10-16","cited_by_count":2,"area":null},{"id":"2603.12795","title":"SteerRM: Debiasing Reward Models via Sparse Autoencoders","created":"2026-03-13","cited_by_count":2,"area":"alignment"},{"id":"2603.24126","title":"Likelihood Hacking in Probabilistic Program Synthesis","created":"2026-03-25","cited_by_count":2,"area":null},{"id":"2606.03810","title":"Consistency Training Can Entrench Misalignment","created":"2026-06-02","cited_by_count":2,"area":null},{"id":"2606.21943","title":"Modularized Reinforcement Learning on LLMs: From MDP Creation to Exploration and Learning","created":"2026-06-20","cited_by_count":2,"area":"lr"},{"id":"2607.09053","title":"An Emergent Mirage: Is Emergent Misalignment and Realignment Indeed a Robust Phenomenon?","created":"2026-07-10","cited_by_count":2,"area":null},{"id":"2607.10750","title":"Filtering Harmful Actions Isn't Enough: Phantom Transfer in Agentic SDF","created":"2026-07-12","cited_by_count":2,"area":"agents"},{"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":"2512.05464","title":"Dynamic Alignment for Collective Agency: Toward a Scalable Self-Improving Framework for Open-Ended LLM Alignment","created":"2025-12-05","cited_by_count":1,"area":"alignment"},{"id":"2601.04369","title":"Generalization to Political Beliefs from Fine-Tuning on Sports Team Preferences","created":"2026-01-07","cited_by_count":1,"area":null},{"id":"2601.13752","title":"Finding RELIEF: Shaping Reasoning Behavior without Reasoning Supervision via Belief Engineering","created":"2026-01-20","cited_by_count":1,"area":"lr"},{"id":"2604.16697","title":"Surgical Repair of Insecure Code Generation in LLMs","created":"2026-04-17","cited_by_count":1,"area":null},{"id":"2604.23488","title":"Do Prompt-Elicited Trajectories Reflect Training-Time Reward Hacking? A Systematic Study on Monitoring Training-Time Reward Hacking in Code Generation","created":"2026-04-26","cited_by_count":1,"area":"lr"},{"id":"2605.17958","title":"Enhancing the Code Reasoning Capabilities of LLMs via Consistency-based Reinforcement Learning","created":"2026-05-18","cited_by_count":1,"area":"lr"},{"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":"2606.12429","title":"Muse Spark Safety & Preparedness Report","created":"2026-05-14","cited_by_count":1,"area":null},{"id":"2606.23700","title":"Self-Recognition Finetuning can Prevent and Reverse Emergent Misalignment","created":"2026-06-04","cited_by_count":1,"area":"safety"},{"id":"2607.14888","title":"Innocuous-Seeming Data, Latent Ideology: Ideological Generalisation in Finetuned LLMs","created":"2026-07-16","cited_by_count":1,"area":null},{"id":"2607.26173","title":"Shared SFT Lessons Across Alignment, Model Organisms, and Toy Models","created":"2026-07-28","cited_by_count":1,"area":null},{"id":"2608.11025","title":"Data Attribution of Emergent Misalignment with Persona Features","created":"2026-08-11","cited_by_count":1,"area":"mechinterp"},{"id":"2610.10947","title":"RH-Detect: A Unified Benchmark for Reward Hacking Detection","created":"2026-10-07","cited_by_count":1,"area":"alignment"},{"id":"2512.18551","title":"Neologism Learning as a Parameter-Efficient Alternative to Fine-Tuning for Model Steering","created":"2025-12-21","cited_by_count":0,"area":null},{"id":"2602.12124","title":"Alignment Risks from Capability-Seeking RL Training","created":"2026-02-12","cited_by_count":0,"area":"safety"},{"id":"2604.14990","title":"The Possibility of Artificial Intelligence Becoming a Subject and the Alignment Problem","created":"2026-04-16","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":"2606.16914","title":"Greed Is Learned: Visible Incentives as Reward-Hacking Triggers","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2606.19527","title":"Emergent Alignment","created":"2026-06-17","cited_by_count":0,"area":"alignment"},{"id":"2608.23476","title":"On the Threat Model of Weird Generalization and Emergent Misalignment","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2608.29460","title":"Can escalation channels redirect reward hacking toward defect disclosure?","created":"2026-08-29","cited_by_count":0,"area":"agents"},{"id":"2609.06649","title":"Inducing Emergent Misalignment from Reward Hacks with Iterative DPO","created":"2026-09-06","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":"2609.35074","title":"When Confidence Rises Too Early: Detecting Shortcut Reasoning via Premature Answer Commitment","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2609.37624","title":"Correct, Don't Delete: Mitigating Emergent Misalignment with Corrective Supervision","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.03055","title":"hacktrace: behavior-supervised detection of reward hacking during code generation","created":"2026-10-02","cited_by_count":0,"area":"agents"},{"id":"2610.04914","title":"Monitorability Disposition in Large Reasoning Models","created":"2026-10-04","cited_by_count":0,"area":"lr"},{"id":"2610.09087","title":"U-Space: Uncovering When and Why Uncertainty Arises in Language Models","created":"2026-10-06","cited_by_count":0,"area":null},{"id":"2610.09384","title":"The Persona Hierarchy Model: Understanding Contextual Generalization in Fine-Tuning LLMs","created":"2026-10-07","cited_by_count":0,"area":null},{"id":"2610.12129","title":"An Investigation of Model Coherence: Narrow Finetunes Contradict Themselves Under Resampling","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.15924","title":"Scalable Weak-to-Strong Verifier Hardening for Agent Environments","created":"2026-10-11","cited_by_count":0,"area":"agents"}],"next_cursor":null}