{"total":82,"rows":[{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065,"area":"lr"},{"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":"2507.11473","title":"Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety","created":"2025-07-15","cited_by_count":249,"area":"lr"},{"id":"2302.08582","title":"Pretraining Language Models with Human Preferences","created":"2023-02-16","cited_by_count":247,"area":"alignment"},{"id":"2302.03648","title":"Class-Incremental Learning: A Survey","created":"2023-02-07","cited_by_count":209,"area":null},{"id":"2404.14367","title":"Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data","created":"2024-04-22","cited_by_count":185,"area":null},{"id":"2402.10207","title":"Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment","created":"2024-02-15","cited_by_count":175,"area":"alignment"},{"id":"2402.09739","title":"QuRating: Selecting High-Quality Data for Training Language Models","created":"2024-02-15","cited_by_count":157,"area":null},{"id":"2302.08500","title":"Auditing large language models: a three-layered approach","created":"2023-02-16","cited_by_count":137,"area":null},{"id":"2406.16838","title":"From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Models","created":"2024-06-24","cited_by_count":137,"area":null},{"id":"2401.01879","title":"Theoretical guarantees on the best-of-n alignment policy","created":"2024-01-03","cited_by_count":124,"area":"lr"},{"id":"2302.08215","title":"Aligning Language Models with Preferences through f-divergence Minimization","created":"2023-02-16","cited_by_count":120,"area":"alignment"},{"id":"2402.14740","title":"Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMs","created":"2024-02-22","cited_by_count":108,"area":"alignment"},{"id":"2504.03380","title":"Online Difficulty Filtering for Reasoning Oriented Reinforcement Learning","created":"2025-04-04","cited_by_count":104,"area":"lr"},{"id":"2510.18874","title":"Retaining by Doing: The Role of On-Policy Data in Mitigating Forgetting","created":"2025-10-21","cited_by_count":94,"area":null},{"id":"2504.05520","title":"Efficient Reinforcement Finetuning via Adaptive Curriculum Learning","created":"2025-04-07","cited_by_count":93,"area":"lr"},{"id":"2401.00243","title":"Uncertainty-Penalized Reinforcement Learning from Human Feedback with Diverse Reward LoRA Ensembles","created":"2023-12-30","cited_by_count":56,"area":"alignment"},{"id":"2407.21035","title":"Direct Unlearning Optimization for Robust and Safe Text-to-Image Models","created":"2024-07-17","cited_by_count":50,"area":"safety"},{"id":"2306.11816","title":"Learning to Generate Better Than Your LLM","created":"2023-06-20","cited_by_count":49,"area":null},{"id":"2404.01730","title":"Asymptotics of Language Model Alignment","created":"2024-04-02","cited_by_count":47,"area":"alignment"},{"id":"2406.16306","title":"Cascade Reward Sampling for Efficient Decoding-Time Alignment","created":"2024-06-24","cited_by_count":39,"area":"alignment"},{"id":"2407.09499","title":"Self-Consuming Generative Models with Curated Data Provably Optimize Human Preferences","created":"2024-06-12","cited_by_count":39,"area":"alignment"},{"id":"2408.01129","title":"A Survey of Mamba","created":"2024-08-02","cited_by_count":39,"area":"ssm"},{"id":"2503.19385","title":"Inference-Time Scaling for Flow Models via Stochastic Generation and Rollover Budget Forcing","created":"2025-03-25","cited_by_count":38,"area":"lr"},{"id":"2509.16679","title":"Reinforcement Learning Meets Large Language Models: A Survey of Advancements and Applications Across the LLM Lifecycle","created":"2025-09-20","cited_by_count":35,"area":null},{"id":"2306.00398","title":"Preference-grounded Token-level Guidance for Language Model Fine-tuning","created":"2023-06-01","cited_by_count":31,"area":"alignment"},{"id":"2510.20817","title":"KL-Regularized Reinforcement Learning is Designed to Mode Collapse","created":"2025-10-23","cited_by_count":31,"area":"deeprl"},{"id":"2503.00735","title":"LADDER: Self-Improving LLMs Through Recursive Problem Decomposition","created":"2025-03-02","cited_by_count":25,"area":"synth"},{"id":"2311.14115","title":"A density estimation perspective on learning from pairwise human preferences","created":"2023-11-23","cited_by_count":23,"area":"alignment"},{"id":"2403.00858","title":"Direct Alignment of Draft Model for Speculative Decoding with Chat-Fine-Tuned LLMs","created":"2024-02-29","cited_by_count":22,"area":"inference"},{"id":"2502.19735","title":"R1-T1: Fully Incentivizing Translation Capability in LLMs via Reasoning Learning","created":"2025-02-27","cited_by_count":21,"area":"lr"},{"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":"2505.11080","title":"BLEUBERI: BLEU is a surprisingly effective reward for instruction following","created":"2025-05-16","cited_by_count":17,"area":"alignment"},{"id":"2406.00049","title":"QUEST: Quality-Aware Metropolis-Hastings Sampling for Machine Translation","created":"2024-05-28","cited_by_count":16,"area":null},{"id":"2507.21183","title":"MaPPO: Maximum a Posteriori Preference Optimization with Prior Knowledge","created":"2025-07-27","cited_by_count":15,"area":"alignment"},{"id":"2410.05328","title":"Reward Learning From Preference With Ties","created":"2024-10-05","cited_by_count":14,"area":"alignment"},{"id":"2402.16030","title":"Don't Forget Your Reward Values: Language Model Alignment via Value-based Calibration","created":"2024-02-25","cited_by_count":13,"area":"alignment"},{"id":"2501.02790","title":"Segmenting Text and Learning Their Rewards for Improved RLHF in Language Model","created":"2025-01-06","cited_by_count":12,"area":"alignment"},{"id":"2411.08302","title":"RED: Unleashing Token-Level Rewards from Holistic Feedback via Reward Redistribution","created":"2024-11-13","cited_by_count":10,"area":"alignment"},{"id":"2505.19428","title":"Frictional Agent Alignment Framework: Slow Down and Don't Break Things","created":"2025-05-26","cited_by_count":10,"area":"agents"},{"id":"2412.13862","title":"Energy-Based Preference Model Offers Better Offline Alignment than the Bradley-Terry Preference Model","created":"2024-12-18","cited_by_count":9,"area":"alignment"},{"id":"2402.02479","title":"BRAIn: Bayesian Reward-conditioned Amortized Inference for natural language generation from feedback","created":"2024-02-04","cited_by_count":7,"area":"alignment"},{"id":"2410.06716","title":"Guaranteed Generation from Large Language Models","created":"2024-10-09","cited_by_count":7,"area":null},{"id":"2605.03327","title":"DGPO: Distribution Guided Policy Optimization for Fine Grained Credit Assignment","created":"2026-05-05","cited_by_count":7,"area":"lr"},{"id":"2409.02718","title":"\"Yes, My LoRD.\" Guiding Language Model Extraction with Locality Reinforced Distillation","created":"2024-09-04","cited_by_count":5,"area":null},{"id":"2603.14128","title":"Diffusion Reinforcement Learning via Centered Reward Distillation","created":"2026-03-14","cited_by_count":5,"area":"diffusion"},{"id":"2502.17721","title":"Aligning Compound AI Systems via System-level DPO","created":"2025-02-24","cited_by_count":4,"area":"alignment"},{"id":"2503.10093","title":"Efficient Safety Alignment of Large Language Models via Preference Re-ranking and Representation-based Reward Modeling","created":"2025-03-13","cited_by_count":4,"area":"alignment"},{"id":"2508.15044","title":"Reward-Shifted Speculative Sampling Is An Efficient Test-Time Weak-to-Strong Aligner","created":"2025-08-20","cited_by_count":4,"area":"alignment"},{"id":"2509.20368","title":"LATTS: Locally Adaptive Test-Time Scaling","created":"2025-09-16","cited_by_count":4,"area":"lr"},{"id":"2303.05431","title":"disco: a toolkit for Distributional Control of Generative Models","created":"2023-03-08","cited_by_count":3,"area":null},{"id":"2406.11039","title":"Dynamic Normativity: Necessary and Sufficient Conditions for Value Alignment","created":"2024-06-16","cited_by_count":3,"area":"alignment"},{"id":"2409.08904","title":"AnyBipe: An End-to-End Framework for Training and Deploying Bipedal Robots Guided by Large Language Models","created":"2024-09-13","cited_by_count":3,"area":null},{"id":"2501.13726","title":"RPO: Retrieval Preference Optimization for Robust Retrieval-Augmented Generation","created":"2025-01-23","cited_by_count":3,"area":"rag"},{"id":"2507.06547","title":"Concept-TRAK: Understanding how diffusion models learn concepts through concept-level attribution","created":"2025-07-09","cited_by_count":3,"area":"diffusion"},{"id":"2510.18353","title":"Ranking-based Preference Optimization for Diffusion Models from Implicit User Feedback","created":"2025-10-21","cited_by_count":3,"area":"diffusion"},{"id":"2512.05962","title":"Whatever Remains Must Be True: Filtering Drives Reasoning in LLMs, Shaping Diversity","created":"2025-12-05","cited_by_count":3,"area":"lr"},{"id":"2601.09253","title":"RIFT: Repurposing Negative Samples via Reward-Informed Fine-Tuning","created":"2026-01-14","cited_by_count":3,"area":"alignment"},{"id":"2410.00508","title":"FlipGuard: Defending Preference Alignment against Update Regression with Constrained Optimization","created":"2024-10-01","cited_by_count":2,"area":"alignment"},{"id":"2505.17242","title":"Optimal Policy Minimum Bayesian Risk","created":"2025-05-22","cited_by_count":2,"area":"lr"},{"id":"2507.13625","title":"Bridging Dual Knowledge Graphs for Multi-Hop Question Answering in Construction Safety","created":"2025-07-18","cited_by_count":2,"area":null},{"id":"2602.16154","title":"Balancing Faithfulness and Performance in Reasoning via Multi-Listener Soft Execution","created":"2026-02-18","cited_by_count":2,"area":"lr"},{"id":"2404.12150","title":"Aligning language models with human preferences","created":"2024-04-18","cited_by_count":1,"area":"alignment"},{"id":"2502.05773","title":"PIPA: Preference Alignment as Prior-Informed Statistical Estimation","created":"2025-02-09","cited_by_count":1,"area":"alignment"},{"id":"2505.23761","title":"Differential Information Distribution: A Bayesian Perspective on Direct Preference Optimization","created":"2025-05-29","cited_by_count":1,"area":"alignment"},{"id":"2506.21129","title":"Curriculum-Adapted Robust Reinforcement Learning for UAV Deconfliction in Adversarial Environments","created":"2025-06-26","cited_by_count":1,"area":"deeprl"},{"id":"2510.00546","title":"ThinkBrake: Efficient Reasoning via Log-Probability Margin Guided Decoding","created":"2025-10-01","cited_by_count":1,"area":"lr"},{"id":"2602.09533","title":"Autoregressive Direct Preference Optimization","created":"2026-02-10","cited_by_count":1,"area":"alignment"},{"id":"2605.02375","title":"Binary Rewards and Reinforcement Learning: Fundamental Challenges","created":"2026-05-04","cited_by_count":1,"area":"lr"},{"id":"2605.10385","title":"Regret Analysis of Guided Diffusion for Black-Box Optimization over Structured Inputs","created":"2026-05-11","cited_by_count":1,"area":"diffusion"},{"id":"2412.07812","title":"Multi-Response Preference Optimization with Augmented Ranking Dataset","created":"2024-12-10","cited_by_count":0,"area":"alignment"},{"id":"2602.10984","title":"Sample Efficient Generative Molecular Optimization with Joint Self-Improvement","created":"2026-02-11","cited_by_count":0,"area":null},{"id":"2602.17366","title":"RPDR: A Round-trip Prediction-Based Data Augmentation Framework for Long-Tail Question Answering","created":"2026-02-19","cited_by_count":0,"area":null},{"id":"2604.18106","title":"Efficient Low-Resource Language Adaptation via Multi-Source Dynamic Logit Fusion","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2605.07545","title":"Implicit Preference Alignment for Human Image Animation","created":"2026-05-08","cited_by_count":0,"area":"alignment"},{"id":"2605.13537","title":"Temper and Tilt Lead to SLOP: Reward Hacking Mitigation with Inference-Time Alignment","created":"2026-05-13","cited_by_count":0,"area":"alignment"},{"id":"2605.24749","title":"How Neural Reward Models Learn Features for Policy Optimization: A Single-Index Analysis","created":"2026-05-23","cited_by_count":0,"area":"alignment"},{"id":"2609.31644","title":"MaD-RL: Matching Distributions for Calibrating LLMs with Reinforcement Learning","created":"2026-09-12","cited_by_count":0,"area":null},{"id":"2609.33426","title":"TeacherGRPO: Closing the Capacity Gap in Reasoning Distillation via Teacher Alignment","created":"2026-09-27","cited_by_count":0,"area":"distill"},{"id":"2609.38689","title":"EPIC: Epipolar-Consistent 360{\\deg} Immersive Stereo Video Generation","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.02015","title":"On Language Drift during RLVR Post-Training","created":"2026-10-01","cited_by_count":0,"area":"lr"},{"id":"2610.17726","title":"TSRL: Trigger-based Supervised Reinforcement Learning for Continual Agent Training","created":"2026-10-13","cited_by_count":0,"area":"lr"}],"next_cursor":null}