{"list":"other","total":51,"rows":[{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"1602.04938","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","created":"2016-02-16","cited_by_count":5070},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720},{"id":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588},{"id":"2106.01946","title":"Convex optimization","created":"2021-06-03","cited_by_count":2515},{"id":"1909.08593","title":"Fine-Tuning Language Models from Human Preferences","created":"2019-09-18","cited_by_count":2150},{"id":"2307.15217","title":"Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback","created":"2023-07-27","cited_by_count":759},{"id":"2310.12773","title":"Safe RLHF: Safe Reinforcement Learning from Human Feedback","created":"2023-10-19","cited_by_count":656},{"id":"2309.00267","title":"RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback","created":"2023-09-01","cited_by_count":625},{"id":"1704.03296","title":"Interpretable Explanations of Black Boxes by Meaningful Perturbation","created":"2017-04-11","cited_by_count":612},{"id":"2308.06463","title":"GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher","created":"2023-08-12","cited_by_count":423},{"id":"2310.10683","title":"Large Language Model Unlearning","created":"2023-10-14","cited_by_count":302},{"id":"2109.13398","title":"Unrolling SGD: Understanding Factors Influencing Machine Unlearning","created":"2021-09-27","cited_by_count":279},{"id":"2312.14925","title":"A Survey of Reinforcement Learning from Human Feedback","created":"2023-12-22","cited_by_count":264},{"id":"2406.15513","title":"PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference","created":"2024-06-20","cited_by_count":261},{"id":"1804.02477","title":"Programmatically Interpretable Reinforcement Learning","created":"2018-04-06","cited_by_count":193},{"id":"2310.10505","title":"ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language Models","created":"2023-10-16","cited_by_count":187},{"id":"1805.08328","title":"Verifiable Reinforcement Learning via Policy Extraction","created":"2018-05-22","cited_by_count":177},{"id":"2402.10058","title":"Towards Safer Large Language Models through Machine Unlearning","created":"2024-02-15","cited_by_count":139},{"id":"2402.15159","title":"Machine Unlearning of Pre-trained Large Language Models","created":"2024-02-23","cited_by_count":119},{"id":"1804.06459","title":"On Learning Intrinsic Rewards for Policy Gradient Methods","created":"2018-04-17","cited_by_count":102},{"id":"1912.05743","title":"Exploratory Not Explanatory: Counterfactual Analysis of Saliency Maps for Deep Reinforcement Learning","created":"2019-12-09","cited_by_count":60},{"id":"1912.12191","title":"Explain Your Move: Understanding Agent Actions Using Specific and Relevant Feature Attribution","created":"2019-12-23","cited_by_count":50},{"id":"2402.02769","title":"Learning from Teaching Regularization: Generalizable Correlations Should be Easy to Imitate","created":"2024-02-05","cited_by_count":47},{"id":"2401.16635","title":"Improving Reinforcement Learning from Human Feedback with Efficient Reward Model Ensemble","created":"2024-01-30","cited_by_count":44},{"id":"2402.17257","title":"RIME: Robust Preference-based Reinforcement Learning with Noisy Preferences","created":"2024-02-27","cited_by_count":39},{"id":"2506.04245","title":"Contextual Integrity in LLMs via Reasoning and Reinforcement Learning","created":"2025-05-29","cited_by_count":31},{"id":"2110.15355","title":"Explaining Latent Representations with a Corpus of Examples","created":"2021-10-28","cited_by_count":30},{"id":"2504.09772","title":"Two Heads are Better Than One: Test-time Scaling of Multi-agent Collaborative Reasoning","created":"2025-04-14","cited_by_count":29},{"id":"2401.11467","title":"Over-Reasoning and Redundant Calculation of Large Language Models","created":"2024-01-21","cited_by_count":27},{"id":"2403.07708","title":"Improving Reinforcement Learning from Human Feedback Using Contrastive Rewards","created":"2024-03-12","cited_by_count":23},{"id":"2312.15023","title":"Federated Q-Learning: Linear Regret Speedup with Low Communication Cost","created":"2023-12-22","cited_by_count":19},{"id":"2410.06554","title":"The Accuracy Paradox in RLHF: When Better Reward Models Don't Yield Better Language Models","created":"2024-10-09","cited_by_count":19},{"id":"2009.04743","title":"TripleTree: A Versatile Interpretable Representation of Black Box Agents and their Environments","created":"2020-09-10","cited_by_count":18},{"id":"2010.15942","title":"Machine versus Human Attention in Deep Reinforcement Learning Tasks","created":"2020-10-29","cited_by_count":16},{"id":"2302.01970","title":"Efficient Gradient Approximation Method for Constrained Bilevel Optimization","created":"2023-02-03","cited_by_count":15},{"id":"2409.14577","title":"AR Overlay: Training Image Pose Estimation on Curved Surface in a Synthetic Way","created":"2024-09-22","cited_by_count":15},{"id":"2508.14313","title":"AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning","created":"2025-08-19","cited_by_count":14},{"id":"2010.05180","title":"Contrastive Explanations for Reinforcement Learning via Embedded Self Predictions","created":"2020-10-11","cited_by_count":13},{"id":"2210.11825","title":"Integrating Policy Summaries with Reward Decomposition for Explaining Reinforcement Learning Agents","created":"2022-10-21","cited_by_count":10},{"id":"2405.18795","title":"Federated Q-Learning with Reference-Advantage Decomposition: Almost Optimal Regret and Logarithmic Communication Cost","created":"2024-05-29","cited_by_count":10},{"id":"2409.07569","title":"A Comprehensive Survey on Inverse Constrained Reinforcement Learning: Definitions, Progress and Challenges","created":"2024-09-11","cited_by_count":10},{"id":"2310.07747","title":"Accountability in Offline Reinforcement Learning: Explaining Decisions with a Corpus of Examples","created":"2023-10-11","cited_by_count":9},{"id":"2410.07574","title":"Gap-Dependent Bounds for Q-Learning using Reference-Advantage Decomposition","created":"2024-10-10","cited_by_count":8},{"id":"2405.03064","title":"RICE: Breaking Through the Training Bottlenecks of Reinforcement Learning with Explanation","created":"2024-05-05","cited_by_count":7},{"id":"2410.15612","title":"In-Trajectory Inverse Reinforcement Learning: Learn Incrementally Before An Ongoing Trajectory Terminates","created":"2024-10-21","cited_by_count":7},{"id":"2507.06266","title":"Machine Learning based Enterprise Financial Audit Framework and High Risk Identification","created":"2025-07-08","cited_by_count":7},{"id":"2502.02859","title":"Gap-Dependent Bounds for Federated $Q$-learning","created":"2025-02-05","cited_by_count":4},{"id":"2409.17359","title":"Data-driven Probabilistic Trajectory Learning with High Temporal Resolution in Terminal Airspace","created":"2024-09-25","cited_by_count":2},{"id":"2410.09728","title":"Meta-Reinforcement Learning with Universal Policy Adaptation: Provable Near-Optimality under All-task Optimum Comparator","created":"2024-10-13","cited_by_count":2}],"next_cursor":null}