{"total":58,"rows":[{"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":"2310.12931","title":"Eureka: Human-Level Reward Design via Coding Large Language Models","created":"2023-10-19","cited_by_count":571,"area":"alignment"},{"id":"1811.07871","title":"Scalable agent alignment via reward modeling: a research direction","created":"2018-11-19","cited_by_count":447,"area":"alignment"},{"id":"2201.03544","title":"The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models","created":"2022-01-10","cited_by_count":328,"area":"alignment"},{"id":"2309.15025","title":"Large Language Model Alignment: A Survey","created":"2023-09-26","cited_by_count":243,"area":"alignment"},{"id":"2209.13085","title":"Defining and Characterizing Reward Hacking","created":"2022-09-27","cited_by_count":203,"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":"2203.10050","title":"SURF: Semi-supervised Reward Learning with Data Augmentation for Feedback-efficient Preference-based Reinforcement Learning","created":"2022-03-18","cited_by_count":97,"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":"2305.15363","title":"Inverse Preference Learning: Preference-based RL without a Reward Function","created":"2023-05-24","cited_by_count":68,"area":"alignment"},{"id":"2205.12401","title":"Reward Uncertainty for Exploration in Preference-based Reinforcement Learning","created":"2022-05-24","cited_by_count":61,"area":"alignment"},{"id":"2206.02231","title":"Models of human preference for learning reward functions","created":"2022-06-05","cited_by_count":54,"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":"2108.05382","title":"Skill Preferences: Learning to Extract and Execute Robotic Skills from Human Feedback","created":"2021-08-11","cited_by_count":35,"area":"alignment"},{"id":"2305.16217","title":"Beyond Reward: Offline Preference-guided Policy Optimization","created":"2023-05-25","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":"2410.14660","title":"A Large Language Model-Driven Reward Design Framework via Dynamic Feedback for Reinforcement Learning","created":"2024-10-18","cited_by_count":30,"area":"alignment"},{"id":"2107.10939","title":"What are you optimizing for? Aligning Recommender Systems with Human Values","created":"2021-07-22","cited_by_count":29,"area":"alignment"},{"id":"2208.10687","title":"The Effect of Modeling Human Rationality Level on Learning Rewards from Multiple Feedback Types","created":"2022-08-23","cited_by_count":26,"area":"alignment"},{"id":"2201.00012","title":"MORAL: Aligning AI with Human Norms through Multi-Objective Reinforced Active Learning","created":"2021-12-30","cited_by_count":25,"area":"alignment"},{"id":"2406.01309","title":"REvolve: Reward Evolution with Large Language Models using Human Feedback","created":"2024-06-03","cited_by_count":23,"area":"alignment"},{"id":"2402.02423","title":"Uni-RLHF: Universal Platform and Benchmark Suite for Reinforcement Learning with Diverse Human Feedback","created":"2024-02-04","cited_by_count":21,"area":"alignment"},{"id":"2101.07691","title":"Choice Set Misspecification in Reward Inference","created":"2021-01-19","cited_by_count":13,"area":"alignment"},{"id":"2205.15367","title":"Non-Markovian Reward Modelling from Trajectory Labels via Interpretable Multiple Instance Learning","created":"2022-05-30","cited_by_count":13,"area":"alignment"},{"id":"2302.13507","title":"Active Reward Learning from Online Preferences","created":"2023-02-27","cited_by_count":13,"area":"alignment"},{"id":"2303.00894","title":"Active Reward Learning from Multiple Teachers","created":"2023-03-02","cited_by_count":13,"area":"alignment"},{"id":"2112.11230","title":"Interpretable Preference-based Reinforcement Learning with Tree-Structured Reward Functions","created":"2021-12-20","cited_by_count":10,"area":"alignment"},{"id":"2401.08672","title":"Concept Alignment","created":"2024-01-09","cited_by_count":10,"area":"alignment"},{"id":"2402.17975","title":"Sample-Efficient Preference-based Reinforcement Learning with Dynamics Aware Rewards","created":"2024-02-28","cited_by_count":9,"area":"alignment"},{"id":"2305.06176","title":"Fine-tuning Language Models with Generative Adversarial Reward Modelling","created":"2023-05-09","cited_by_count":8,"area":"alignment"},{"id":"2405.14769","title":"Pragmatic Feature Preferences: Learning Reward-Relevant Preferences from Human Input","created":"2024-05-23","cited_by_count":8,"area":"alignment"},{"id":"2503.00069","title":"Societal Alignment Frameworks Can Improve LLM Alignment","created":"2025-02-27","cited_by_count":8,"area":"alignment"},{"id":"2204.07123","title":"Retrospective on the 2021 BASALT Competition on Learning from Human Feedback","created":"2022-04-14","cited_by_count":5,"area":"alignment"},{"id":"2211.06527","title":"Rewards Encoding Environment Dynamics Improves Preference-based Reinforcement Learning","created":"2022-11-12","cited_by_count":4,"area":"alignment"},{"id":"2302.08733","title":"Data Driven Reward Initialization for Preference based Reinforcement Learning","created":"2023-02-17","cited_by_count":3,"area":"alignment"},{"id":"2410.05782","title":"Reinforcement Learning From Imperfect Corrective Actions And Proxy Rewards","created":"2024-10-08","cited_by_count":3,"area":"alignment"},{"id":"2504.10002","title":"FLoRA: Sample-Efficient Preference-based RL via Low-Rank Style Adaptation of Reward Functions","created":"2025-04-14","cited_by_count":3,"area":"alignment"},{"id":"2506.09508","title":"Efficient Preference-Based Reinforcement Learning: Randomized Exploration Meets Experimental Design","created":"2025-06-11","cited_by_count":3,"area":"alignment"},{"id":"2511.13765","title":"PROF: An LLM-based Reward Code Preference Optimization Framework for Offline Imitation Learning","created":"2025-11-14","cited_by_count":3,"area":"alignment"},{"id":"2605.27851","title":"When Context Flips, Safety Breaks: Diagnosing Brittle Safety in Aligned Language Models","created":"2026-05-27","cited_by_count":3,"area":"alignment"},{"id":"2302.08734","title":"A State Augmentation based approach to Reinforcement Learning from Human Preferences","created":"2023-02-17","cited_by_count":2,"area":"alignment"},{"id":"2307.05405","title":"Boosting Feedback Efficiency of Interactive Reinforcement Learning by Adaptive Learning from Scores","created":"2023-07-11","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":"2507.00611","title":"Residual Reward Models: Leveraging Prior Knowledge for Efficient Preference-based Reinforcement Learning in Robotics","created":"2025-07-01","cited_by_count":1,"area":"alignment"},{"id":"2510.06092","title":"Learning from Failures: Understanding LLM Alignment through Failure-Aware Inverse RL","created":"2025-10-07","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":"2604.26360","title":"Uncertainty-Aware Reward Discounting for Mitigating Reward Hacking","created":"2026-04-29","cited_by_count":1,"area":"alignment"},{"id":"2205.07882","title":"Aligning Robot Representations with Humans","created":"2022-05-15","cited_by_count":0,"area":"alignment"},{"id":"2302.12349","title":"Reward Learning as Doubly Nonparametric Bandits: Optimal Design and Scaling Laws","created":"2023-02-23","cited_by_count":0,"area":"alignment"},{"id":"2401.05710","title":"The Distributional Reward Critic Framework for Reinforcement Learning Under Perturbed Rewards","created":"2024-01-11","cited_by_count":0,"area":"alignment"},{"id":"2412.07990","title":"Adaptive Querying for Reward Learning from Human Feedback","created":"2024-12-11","cited_by_count":0,"area":"alignment"},{"id":"2412.21001","title":"LEASE: Offline Preference-based Reinforcement Learning with High Sample Efficiency","created":"2024-12-30","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"},{"id":"2602.18582","title":"Hierarchical Reward Design from Language: Enhancing Alignment of Agent Behavior with Human Specifications","created":"2026-02-20","cited_by_count":0,"area":"alignment"},{"id":"2604.04237","title":"Pedagogical Safety in Educational Reinforcement Learning: Formalizing and Detecting Reward Hacking in AI Tutoring Systems","created":"2026-04-05","cited_by_count":0,"area":"alignment"},{"id":"2604.24155","title":"The Alignment Target Problem: Divergent Moral Judgments of Humans, AI Systems, and Their Designers","created":"2026-04-27","cited_by_count":0,"area":"alignment"},{"id":"2609.04066","title":"Subspace Inference Enables Efficient Active Reward Learning from Preferences","created":"2026-09-03","cited_by_count":0,"area":"alignment"},{"id":"2609.09685","title":"ALIGN-HOLD: Experience Alignment for Real-Time Hold Control in Large-Scale Ride-Hailing Matching at DiDi","created":"2026-09-09","cited_by_count":0,"area":"alignment"}],"next_cursor":null}