{"total":119,"rows":[{"id":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720,"area":"alignment"},{"id":"2210.10760","title":"Scaling Laws for Reward Model Overoptimization","created":"2022-10-19","cited_by_count":1095,"area":"alignment"},{"id":"2307.15217","title":"Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback","created":"2023-07-27","cited_by_count":759,"area":"alignment"},{"id":"2306.04488","title":"Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards","created":"2023-06-07","cited_by_count":243,"area":"alignment"},{"id":"2310.02743","title":"Reward Model Ensembles Help Mitigate Overoptimization","created":"2023-10-04","cited_by_count":231,"area":"alignment"},{"id":"2209.13085","title":"Defining and Characterizing Reward Hacking","created":"2022-09-27","cited_by_count":203,"area":"alignment"},{"id":"2312.09244","title":"Helping or Herding? Reward Model Ensembles Mitigate but do not Eliminate Reward Hacking","created":"2023-12-14","cited_by_count":200,"area":"alignment"},{"id":"2403.19159","title":"Disentangling Length from Quality in Direct Preference Optimization","created":"2024-03-28","cited_by_count":196,"area":"alignment"},{"id":"2304.11082","title":"Fundamental Limitations of Alignment in Large Language Models","created":"2023-04-19","cited_by_count":155,"area":"alignment"},{"id":"2401.12187","title":"WARM: On the Benefits of Weight Averaged Reward Models","created":"2024-01-22","cited_by_count":147,"area":"alignment"},{"id":"2406.02900","title":"Scaling Laws for Reward Model Overoptimization in Direct Alignment Algorithms","created":"2024-06-05","cited_by_count":143,"area":"alignment"},{"id":"2403.08635","title":"Human Alignment of Large Language Models through Online Preference Optimisation","created":"2024-03-13","cited_by_count":91,"area":"alignment"},{"id":"2404.08555","title":"RLHF Deciphered: A Critical Analysis of Reinforcement Learning from Human Feedback for LLMs","created":"2024-04-12","cited_by_count":90,"area":"alignment"},{"id":"2305.16960","title":"Training Socially Aligned Language Models on Simulated Social Interactions","created":"2023-05-26","cited_by_count":78,"area":"alignment"},{"id":"2310.05199","title":"Loose lips sink ships: Mitigating Length Bias in Reinforcement Learning from Human Feedback","created":"2023-10-08","cited_by_count":78,"area":"alignment"},{"id":"2402.06627","title":"Feedback Loops With Language Models Drive In-Context Reward Hacking","created":"2024-02-09","cited_by_count":77,"area":"alignment"},{"id":"2407.14622","title":"BOND: Aligning LLMs with Best-of-N Distillation","created":"2024-07-19","cited_by_count":76,"area":"alignment"},{"id":"2402.02992","title":"Decoding-time Realignment of Language Models","created":"2024-02-05","cited_by_count":67,"area":"alignment"},{"id":"2310.05910","title":"SALMON: Self-Alignment with Instructable Reward Models","created":"2023-10-09","cited_by_count":55,"area":"alignment"},{"id":"2204.06601","title":"Causal Confusion and Reward Misidentification in Preference-Based Reward Learning","created":"2022-04-13","cited_by_count":53,"area":"alignment"},{"id":"2403.03185","title":"Correlated Proxies: A New Definition and Improved Mitigation for Reward Hacking","created":"2024-03-05","cited_by_count":50,"area":"alignment"},{"id":"2405.19107","title":"Offline Regularised Reinforcement Learning for Large Language Models Alignment","created":"2024-05-29","cited_by_count":48,"area":"alignment"},{"id":"2406.16768","title":"WARP: On the Benefits of Weight Averaged Rewarded Policies","created":"2024-06-24","cited_by_count":45,"area":"alignment"},{"id":"2409.20370","title":"The Perfect Blend: Redefining RLHF with Mixture of Judges","created":"2024-09-30","cited_by_count":43,"area":"alignment"},{"id":"2510.05024","title":"Inoculation Prompting: Instructing LLMs to misbehave at train-time improves test-time alignment","created":"2025-10-06","cited_by_count":43,"area":"alignment"},{"id":"2311.00168","title":"The Alignment Ceiling: Objective Mismatch in Reinforcement Learning from Human Feedback","created":"2023-10-31","cited_by_count":42,"area":"alignment"},{"id":"2501.09620","title":"Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment","created":"2025-01-16","cited_by_count":42,"area":"alignment"},{"id":"2502.12668","title":"Evaluation of Best-of-N Sampling Strategies for Language Model Alignment","created":"2025-02-18","cited_by_count":39,"area":"alignment"},{"id":"2404.05530","title":"Best-of-Venom: Attacking RLHF by Injecting Poisoned Preference Data","created":"2024-04-08","cited_by_count":35,"area":"alignment"},{"id":"2412.19792","title":"InfAlign: Inference-aware language model alignment","created":"2024-12-27","cited_by_count":35,"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":"2403.05171","title":"Overcoming Reward Overoptimization via Adversarial Policy Optimization with Lightweight Uncertainty Estimation","created":"2024-03-08","cited_by_count":33,"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":"2511.23002","title":"JarvisEvo: Towards a Self-Evolving Photo Editing Agent with Synergistic Editor-Evaluator Optimization","created":"2025-11-28","cited_by_count":31,"area":"alignment"},{"id":"2401.16332","title":"Tradeoffs Between Alignment and Helpfulness in Language Models with Steering Methods","created":"2024-01-29","cited_by_count":28,"area":"alignment"},{"id":"2408.04655","title":"Strong and weak alignment of large language models with human values","created":"2024-08-05","cited_by_count":27,"area":"alignment"},{"id":"2310.11971","title":"Improving Generalization of Alignment with Human Preferences through Group Invariant Learning","created":"2023-10-18","cited_by_count":25,"area":"alignment"},{"id":"2404.01054","title":"Regularized Best-of-N Sampling with Minimum Bayes Risk Objective for Language Model Alignment","created":"2024-04-01","cited_by_count":25,"area":"alignment"},{"id":"2301.03652","title":"On The Fragility of Learned Reward Functions","created":"2023-01-09","cited_by_count":21,"area":"alignment"},{"id":"2403.04204","title":"On the Essence and Prospect: An Investigation of Alignment Approaches for Big Models","created":"2024-03-07","cited_by_count":21,"area":"alignment"},{"id":"2309.09055","title":"Exploring the impact of low-rank adaptation on the performance, efficiency, and regularization of RLHF","created":"2023-09-16","cited_by_count":20,"area":"alignment"},{"id":"2506.16507","title":"Robust Reward Modeling via Causal Rubrics","created":"2025-06-19","cited_by_count":19,"area":"alignment"},{"id":"2507.05619","title":"Detecting Proxy Gaming in RL and LLM Alignment via Evaluator Stress Tests","created":"2025-07-08","cited_by_count":19,"area":"alignment"},{"id":"2406.09264","title":"Position: Towards Bidirectional Human-AI Alignment","created":"2024-06-13","cited_by_count":18,"area":"alignment"},{"id":"2509.23082","title":"Follow-Your-Preference: Towards Preference-Aligned Image Inpainting","created":"2025-09-27","cited_by_count":18,"area":"alignment"},{"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":"2406.04274","title":"Self-Play with Adversarial Critic: Provable and Scalable Offline Alignment for Language Models","created":"2024-06-06","cited_by_count":16,"area":"alignment"},{"id":"2403.18742","title":"Understanding the Learning Dynamics of Alignment with Human Feedback","created":"2024-03-27","cited_by_count":15,"area":"alignment"},{"id":"2507.21183","title":"MaPPO: Maximum a Posteriori Preference Optimization with Prior Knowledge","created":"2025-07-27","cited_by_count":15,"area":"alignment"},{"id":"2603.08035","title":"CDRRM: Contrast-Driven Rubric Generation for Reliable and Interpretable Reward Modeling","created":"2026-03-09","cited_by_count":12,"area":"alignment"},{"id":"2406.14393","title":"Jailbreaking as a Reward Misspecification Problem","created":"2024-06-20","cited_by_count":11,"area":"alignment"},{"id":"2412.08812","title":"Test-Time Alignment via Hypothesis Reweighting","created":"2024-12-11","cited_by_count":11,"area":"alignment"},{"id":"2502.18699","title":"MPO: An Efficient Post-Processing Framework for Mixing Diverse Preference Alignment","created":"2025-02-25","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":"2307.00279","title":"Let Me Teach You: Pedagogical Foundations of Feedback for Language Models","created":"2023-07-01","cited_by_count":9,"area":"alignment"},{"id":"2409.00162","title":"Sequence to Sequence Reward Modeling: Improving RLHF by Language Feedback","created":"2024-08-30","cited_by_count":9,"area":"alignment"},{"id":"2608.11669","title":"Rubric Dropout: A Simple Way to Mitigate Reward Hacking in Rubric-as-Reward RL","created":"2026-08-12","cited_by_count":9,"area":"alignment"},{"id":"2410.06491","title":"Honesty to Subterfuge: In-Context Reinforcement Learning Can Make Honest Models Reward Hack","created":"2024-10-09","cited_by_count":8,"area":"alignment"},{"id":"2410.11348","title":"RATE: Causal Explainability of Reward Models with Imperfect Counterfactuals","created":"2024-10-15","cited_by_count":8,"area":"alignment"},{"id":"2408.03459","title":"Can DPO Learn Diverse Human Values? A Theoretical Scaling Law","created":"2024-08-06","cited_by_count":7,"area":"alignment"},{"id":"2512.23461","title":"Eliminating Inductive Bias in Reward Models with Information-Theoretic Guidance","created":"2025-12-29","cited_by_count":7,"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":"2502.00814","title":"Disentangling Length Bias In Preference Learning Via Response-Conditioned Modeling","created":"2025-02-02","cited_by_count":6,"area":"alignment"},{"id":"2505.10597","title":"Two Minds Better Than One: Collaborative Reward Modeling for LLM Alignment","created":"2025-05-15","cited_by_count":6,"area":"alignment"},{"id":"2507.18742","title":"Specification Self-Correction: Mitigating In-Context Reward Hacking Through Test-Time Refinement","created":"2025-07-24","cited_by_count":6,"area":"alignment"},{"id":"2510.14616","title":"Beyond Correctness: Evaluating Subjective Writing Preferences Across Cultures","created":"2025-10-16","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":"2401.07181","title":"Reinforcement Learning from LLM Feedback to Counteract Goal Misgeneralization","created":"2024-01-14","cited_by_count":5,"area":"alignment"},{"id":"2406.07971","title":"It Takes Two: On the Seamlessness between Reward and Policy Model in RLHF","created":"2024-06-12","cited_by_count":5,"area":"alignment"},{"id":"2505.17122","title":"Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data?","created":"2025-05-21","cited_by_count":5,"area":"alignment"},{"id":"2603.28063","title":"Reward Hacking as Equilibrium under Finite Evaluation","created":"2026-03-30","cited_by_count":5,"area":"alignment"},{"id":"2506.05070","title":"RIVAL: Reinforcement Learning with Iterative and Adversarial Optimization for Machine Translation","created":"2025-06-05","cited_by_count":4,"area":"alignment"},{"id":"2604.02507","title":"Reinforcement Learning from Human Feedback: A Statistical Perspective","created":"2026-04-02","cited_by_count":4,"area":"alignment"},{"id":"2406.11039","title":"Dynamic Normativity: Necessary and Sufficient Conditions for Value Alignment","created":"2024-06-16","cited_by_count":3,"area":"alignment"},{"id":"2510.01458","title":"How Well Can Preference Optimization Generalize Under Noisy Feedback?","created":"2025-10-01","cited_by_count":3,"area":"alignment"},{"id":"2512.23067","title":"The Reward Model Selection Crisis in Personalized Alignment","created":"2025-12-28","cited_by_count":3,"area":"alignment"},{"id":"2210.01007","title":"Reward Learning with Trees: Methods and Evaluation","created":"2022-10-03","cited_by_count":2,"area":"alignment"},{"id":"2308.15969","title":"Iterative Reward Shaping using Human Feedback for Correcting Reward Misspecification","created":"2023-08-30","cited_by_count":2,"area":"alignment"},{"id":"2503.03122","title":"The Devil Is in the Details: Tackling Unimodal Spurious Correlations for Generalizable Multimodal Reward Models","created":"2025-03-05","cited_by_count":2,"area":"alignment"},{"id":"2509.23564","title":"Clean First, Align Later: Benchmarking Preference Data Cleaning for Reliable LLM Alignment","created":"2025-09-28","cited_by_count":2,"area":"alignment"},{"id":"2601.01904","title":"Evaluating Feature Dependent Noise in Preference-based Reinforcement Learning","created":"2026-01-05","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":"2402.04856","title":"Explaining Learned Reward Functions with Counterfactual Trajectories","created":"2024-02-07","cited_by_count":1,"area":"alignment"},{"id":"2404.08791","title":"Expectation Alignment: Handling Reward Misspecification in the Presence of Expectation Mismatch","created":"2024-04-12","cited_by_count":1,"area":"alignment"},{"id":"2404.12150","title":"Aligning language models with human preferences","created":"2024-04-18","cited_by_count":1,"area":"alignment"},{"id":"2412.16475","title":"When Can Proxies Improve the Sample Complexity of Preference Learning?","created":"2024-12-21","cited_by_count":1,"area":"alignment"},{"id":"2504.14838","title":"Establishing Reliability Metrics for Reward Models in Large Language Models","created":"2025-04-21","cited_by_count":1,"area":"alignment"},{"id":"2510.13036","title":"Repairing Reward Functions with Feedback to Mitigate Reward Hacking","created":"2025-10-14","cited_by_count":1,"area":"alignment"},{"id":"2512.20173","title":"Offline Safe Policy Optimization From Heterogeneous Feedback","created":"2025-12-23","cited_by_count":1,"area":"alignment"},{"id":"2603.02225","title":"Scaling Reward Modeling without Human Supervision","created":"2026-02-11","cited_by_count":1,"area":"alignment"},{"id":"2605.16339","title":"Preference Instability in Reward Models: Detection and Mitigation via Sparse Autoencoders","created":"2026-05-07","cited_by_count":1,"area":"alignment"},{"id":"2606.04145","title":"EvalStop: Using World Feedback to Detect and Correct Reward Overoptimization in Multi-Tenant RLHF Platforms","created":"2026-06-02","cited_by_count":1,"area":"alignment"},{"id":"2606.09073","title":"A Unifying Lens on Reward Uncertainty in RLHF","created":"2026-06-08","cited_by_count":1,"area":"alignment"},{"id":"2609.25270","title":"RULER: Instance-aware Rubric Rewards for SVG Generation","created":"2026-09-21","cited_by_count":1,"area":"alignment"},{"id":"2609.36308","title":"CheatBench: Measuring Reward Gaming in AI Agents","created":"2026-09-28","cited_by_count":1,"area":"alignment"},{"id":"2407.14681","title":"Value Internalization: Learning and Generalizing from Social Reward","created":"2024-07-19","cited_by_count":0,"area":"alignment"},{"id":"2503.04346","title":"Adding Alignment Control to Language Models","created":"2025-03-06","cited_by_count":0,"area":"alignment"},{"id":"2506.09329","title":"Towards Efficient and Effective Alignment of Large Language Models","created":"2025-06-11","cited_by_count":0,"area":"alignment"},{"id":"2509.20265","title":"Failure Modes of Maximum Entropy RLHF","created":"2025-09-24","cited_by_count":0,"area":"alignment"}],"next_cursor":"100"}