{"total":101,"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":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588,"area":"alignment"},{"id":"1909.08593","title":"Fine-Tuning Language Models from Human Preferences","created":"2019-09-18","cited_by_count":2150,"area":"alignment"},{"id":"2202.03286","title":"Red Teaming Language Models with Language Models","created":"2022-02-07","cited_by_count":1026,"area":"safety"},{"id":"2309.00267","title":"RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback","created":"2023-09-01","cited_by_count":625,"area":"alignment"},{"id":"2305.10425","title":"SLiC-HF: Sequence Likelihood Calibration with Human Feedback","created":"2023-05-17","cited_by_count":401,"area":"alignment"},{"id":"2310.06452","title":"Understanding the Effects of RLHF on LLM Generalisation and Diversity","created":"2023-10-10","cited_by_count":396,"area":"alignment"},{"id":"2203.11147","title":"Teaching language models to support answers with verified quotes","created":"2022-03-21","cited_by_count":292,"area":null},{"id":"1907.00456","title":"Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog","created":"2019-06-30","cited_by_count":284,"area":"offlinerl"},{"id":"2103.08050","title":"Offline Reinforcement Learning with Fisher Divergence Critic Regularization","created":"2021-03-14","cited_by_count":238,"area":"offlinerl"},{"id":"2002.08396","title":"Keep Doing What Worked: Behavioral Modelling Priors for Offline Reinforcement Learning","created":"2020-02-19","cited_by_count":215,"area":"offlinerl"},{"id":"2303.04129","title":"Foundation Models for Decision Making: Problems, Methods, and Opportunities","created":"2023-03-07","cited_by_count":164,"area":null},{"id":"2401.12187","title":"WARM: On the Benefits of Weight Averaged Reward Models","created":"2024-01-22","cited_by_count":147,"area":"alignment"},{"id":"2206.11871","title":"Offline RL for Natural Language Generation with Implicit Language Q Learning","created":"2022-06-05","cited_by_count":138,"area":"offlinerl"},{"id":"2205.11275","title":"RL with KL penalties is better viewed as Bayesian inference","created":"2022-05-23","cited_by_count":135,"area":null},{"id":"2302.08215","title":"Aligning Language Models with Preferences through f-divergence Minimization","created":"2023-02-16","cited_by_count":120,"area":"alignment"},{"id":"1910.01708","title":"Benchmarking Batch Deep Reinforcement Learning Algorithms","created":"2019-10-03","cited_by_count":111,"area":"offlinerl"},{"id":"2010.05848","title":"Human-centric Dialog Training via Offline Reinforcement Learning","created":"2020-10-12","cited_by_count":93,"area":"offlinerl"},{"id":"2311.18232","title":"LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Models","created":"2023-11-30","cited_by_count":88,"area":null},{"id":"2206.00761","title":"On Reinforcement Learning and Distribution Matching for Fine-Tuning Language Models with no Catastrophic Forgetting","created":"2022-06-01","cited_by_count":82,"area":null},{"id":"2306.00186","title":"Factually Consistent Summarization via Reinforcement Learning with Textual Entailment Feedback","created":"2023-05-31","cited_by_count":72,"area":null},{"id":"2410.08193","title":"GenARM: Reward Guided Generation with Autoregressive Reward Model for Test-time Alignment","created":"2024-10-10","cited_by_count":54,"area":"alignment"},{"id":"2405.19534","title":"Preference Learning Algorithms Do Not Learn Preference Rankings","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":"2405.13021","title":"IM-RAG: Multi-Round Retrieval-Augmented Generation Through Learning Inner Monologues","created":"2024-05-15","cited_by_count":40,"area":"rag"},{"id":"2410.01639","title":"Moral Alignment for LLM Agents","created":"2024-10-02","cited_by_count":39,"area":"agents"},{"id":"2506.07468","title":"Chasing Moving Targets with Online Self-Play Reinforcement Learning for Safer Language Models","created":"2025-06-09","cited_by_count":39,"area":"alignment"},{"id":"2106.07704","title":"Efficient (Soft) Q-Learning for Text Generation with Limited Good Data","created":"2021-06-14","cited_by_count":37,"area":null},{"id":"2312.07551","title":"Language Model Alignment with Elastic Reset","created":"2023-12-06","cited_by_count":34,"area":"alignment"},{"id":"2402.04229","title":"MusicRL: Aligning Music Generation to Human Preferences","created":"2024-02-06","cited_by_count":32,"area":"alignment"},{"id":"2504.19599","title":"GVPO: Group Variance Policy Optimization for Large Language Model Post-Training","created":"2025-04-28","cited_by_count":32,"area":"alignment"},{"id":"2504.03206","title":"Enhancing Personalized Multi-Turn Dialogue with Curiosity Reward","created":"2025-04-04","cited_by_count":27,"area":"alignment"},{"id":"2104.02726","title":"Creativity and Machine Learning: A Survey","created":"2021-04-06","cited_by_count":21,"area":null},{"id":"2407.02446","title":"Predicting vs. Acting: A Trade-off Between World Modeling & Agent Modeling","created":"2024-07-02","cited_by_count":20,"area":"wm"},{"id":"2312.03631","title":"Mitigating Open-Vocabulary Caption Hallucinations","created":"2023-12-06","cited_by_count":19,"area":null},{"id":"2509.26314","title":"Latent Thinking Optimization: Your Latent Reasoning Language Model Secretly Encodes Reward Signals in Its Latent Thoughts","created":"2025-09-30","cited_by_count":19,"area":"lr"},{"id":"2512.21852","title":"A Comedy of Estimators: On KL Regularization in RL Training of LLMs","created":"2025-12-26","cited_by_count":18,"area":"lr"},{"id":"2103.12726","title":"Policy Information Capacity: Information-Theoretic Measure for Task Complexity in Deep Reinforcement Learning","created":"2021-03-23","cited_by_count":15,"area":null},{"id":"2103.17258","title":"Co-Adaptation of Algorithmic and Implementational Innovations in Inference-based Deep Reinforcement Learning","created":"2021-03-31","cited_by_count":15,"area":null},{"id":"2412.05818","title":"SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation","created":"2024-12-08","cited_by_count":15,"area":"mllm"},{"id":"2507.19672","title":"Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges","created":"2025-07-25","cited_by_count":15,"area":"alignment"},{"id":"2508.06249","title":"In-Training Defenses against Emergent Misalignment in Language Models","created":"2025-08-08","cited_by_count":15,"area":"alignment"},{"id":"2406.19185","title":"Contrastive Policy Gradient: Aligning LLMs on sequence-level scores in a supervised-friendly fashion","created":"2024-06-27","cited_by_count":13,"area":"alignment"},{"id":"2504.02367","title":"Reinforcement Fine-Tuning for Materials Design","created":"2025-04-03","cited_by_count":13,"area":null},{"id":"2503.05453","title":"Soft Policy Optimization: Online Off-Policy RL for Sequence Models","created":"2025-03-07","cited_by_count":12,"area":null},{"id":"2308.14328","title":"Reinforcement Learning for Generative AI: A Survey","created":"2023-08-28","cited_by_count":11,"area":null},{"id":"2308.00031","title":"Reinforcement Learning for Generative AI: State of the Art, Opportunities and Open Research Challenges","created":"2023-07-31","cited_by_count":10,"area":null},{"id":"2410.06084","title":"Diversity-Rewarded CFG Distillation","created":"2024-10-08","cited_by_count":9,"area":null},{"id":"2504.05181","title":"Lightweight and Direct Document Relevance Optimization for Generative Information Retrieval","created":"2025-04-07","cited_by_count":9,"area":null},{"id":"2505.23349","title":"Towards Reward Fairness in RLHF: From a Resource Allocation Perspective","created":"2025-05-29","cited_by_count":9,"area":"alignment"},{"id":"2205.12381","title":"First Contact: Unsupervised Human-Machine Co-Adaptation via Mutual Information Maximization","created":"2022-05-24","cited_by_count":8,"area":null},{"id":"2601.02036","title":"GDRO: Group-level Reward Post-training Suitable for Diffusion Models","created":"2026-01-05","cited_by_count":8,"area":"diffusion"},{"id":"2308.09970","title":"Tackling Vision Language Tasks Through Learning Inner Monologues","created":"2023-08-19","cited_by_count":7,"area":null},{"id":"2507.08390","title":"Inference-Time Scaling of Diffusion Language Models via Trajectory Refinement","created":"2025-07-11","cited_by_count":7,"area":"lr"},{"id":"2507.08068","title":"Quantile Reward Policy Optimization: Alignment with Pointwise Regression and Exact Partition Functions","created":"2025-07-10","cited_by_count":6,"area":"lr"},{"id":"2406.19188","title":"Averaging log-likelihoods in direct alignment","created":"2024-06-27","cited_by_count":5,"area":"alignment"},{"id":"2509.01632","title":"Relative Trajectory Balance is equivalent to Trust-PCL","created":"2025-09-01","cited_by_count":5,"area":"diffusion"},{"id":"2605.23346","title":"Contrastive Distribution Matching for Amortized Sequential Monte Carlo in Discrete Diffusion","created":"2026-05-22","cited_by_count":5,"area":"diffusion"},{"id":"2203.02072","title":"X2T: Training an X-to-Text Typing Interface with Online Learning from User Feedback","created":"2022-03-04","cited_by_count":4,"area":null},{"id":"2502.12579","title":"CHATS: Combining Human-Aligned Optimization and Test-Time Sampling for Text-to-Image Generation","created":"2025-02-18","cited_by_count":4,"area":"diffusion"},{"id":"2502.19255","title":"Can RLHF be More Efficient with Imperfect Reward Models? A Policy Coverage Perspective","created":"2025-02-26","cited_by_count":4,"area":"alignment"},{"id":"2506.14723","title":"Adaptive Accompaniment with ReaLchords","created":"2025-06-17","cited_by_count":4,"area":null},{"id":"2605.04266","title":"Explaining and Preventing Alignment Collapse in Iterative RLHF","created":"2026-05-05","cited_by_count":4,"area":"alignment"},{"id":"2605.21123","title":"Linear-DPO: Linear Direct Preference Optimization for Diffusion and Flow-Matching Generative Models","created":"2026-05-20","cited_by_count":4,"area":"diffusion"},{"id":"2112.01625","title":"Sample-Efficient Generation of Novel Photo-acid Generator Molecules using a Deep Generative Model","created":"2021-12-02","cited_by_count":3,"area":null},{"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":"2511.17879","title":"Generative Adversarial Post-Training Mitigates Reward Hacking in Live Human-AI Music Interaction","created":"2025-11-22","cited_by_count":3,"area":"alignment"},{"id":"2602.00413","title":"Alignment of Diffusion Model and Flow Matching for Text-to-Image Generation","created":"2026-01-31","cited_by_count":3,"area":"diffusion"},{"id":"2109.09371","title":"Learning Natural Language Generation from Scratch","created":"2021-09-20","cited_by_count":2,"area":null},{"id":"2405.11904","title":"A Constraint-Enforcing Reward for Adversarial Attacks on Text Classifiers","created":"2024-05-20","cited_by_count":2,"area":null},{"id":"2410.06213","title":"RL, but don't do anything I wouldn't do","created":"2024-10-08","cited_by_count":2,"area":"deeprl"},{"id":"2502.12776","title":"Portable Reward Tuning: Towards Reusable Fine-Tuning across Different Pretrained Models","created":"2025-02-18","cited_by_count":2,"area":"lr"},{"id":"2503.11019","title":"Residual Policy Gradient: A Reward View of KL-regularized Objective","created":"2025-03-14","cited_by_count":2,"area":"offlinerl"},{"id":"2503.17965","title":"Understanding the Effects of RLHF on the Quality and Detectability of LLM-Generated Texts","created":"2025-03-23","cited_by_count":2,"area":"alignment"},{"id":"2507.02255","title":"Listwise Preference Alignment Optimization for Tail Item Recommendation","created":"2025-07-03","cited_by_count":2,"area":"alignment"},{"id":"2511.01450","title":"Reg-DPO: SFT-Regularized Direct Preference Optimization with GT-Pair for Improving Video Generation","created":"2025-11-03","cited_by_count":2,"area":"alignment"},{"id":"2511.12113","title":"MetaGDPO: Alleviating Catastrophic Forgetting with Metacognitive Knowledge through Group Direct Preference Optimization","created":"2025-11-15","cited_by_count":2,"area":"lr"},{"id":"2608.24949","title":"Demystifying Reinforcement Learning Post-Training of Language Models","created":"2026-08-24","cited_by_count":2,"area":"lr"},{"id":"2310.09017","title":"Dont Add, dont Miss: Effective Content Preserving Generation from Pre-Selected Text Spans","created":"2023-10-13","cited_by_count":1,"area":null},{"id":"2504.02646","title":"Prompt Optimization with Logged Bandit Data","created":"2025-04-03","cited_by_count":1,"area":null},{"id":"2509.26169","title":"Alignment-Aware Decoding","created":"2025-09-30","cited_by_count":1,"area":"alignment"},{"id":"2510.10077","title":"A-IPO: Adaptive Intent-driven Preference Optimization","created":"2025-10-11","cited_by_count":1,"area":"alignment"},{"id":"2512.15765","title":"Shapley-based Data Valuation for LLM Alignment via Sequential Preference Optimization","created":"2025-12-12","cited_by_count":1,"area":"alignment"},{"id":"2601.20198","title":"DeRaDiff: Denoising Time Realignment of Diffusion Models","created":"2026-01-28","cited_by_count":1,"area":"diffusion"},{"id":"2602.07799","title":"Fairness Aware Reward Optimization","created":"2026-02-08","cited_by_count":1,"area":"alignment"},{"id":"2609.14896","title":"Forty Shades of Blue: Quality-Diversity Alignment via Mode-Conditioned Reinforcement Learning","created":"2026-09-14","cited_by_count":1,"area":"alignment"},{"id":"2310.04483","title":"Reward Dropout Improves Control: Bi-objective Perspective on Reinforced LM","created":"2023-10-06","cited_by_count":0,"area":null},{"id":"2403.01306","title":"ICC: Quantifying Image Caption Concreteness for Multimodal Dataset Curation","created":"2024-03-02","cited_by_count":0,"area":null},{"id":"2410.03989","title":"Symmetry From Scratch: Group Equivariance as a Supervised Learning Task","created":"2024-10-05","cited_by_count":0,"area":null},{"id":"2507.02173","title":"Data Diversification Methods In Alignment Enhance Math Performance In LLMs","created":"2025-07-02","cited_by_count":0,"area":"lr"},{"id":"2603.19294","title":"Maximizing Mutual Information Between Prompt and Response Improves LLM Performance With No Additional Data","created":"2026-03-10","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":"2605.14062","title":"Know When To Fold 'Em: Token-Efficient LLM Synthetic Data Generation via Multi-Stage In-Flight Rejection","created":"2026-05-13","cited_by_count":0,"area":"synth"},{"id":"2606.18537","title":"Do as the Romans Do: Learning Universal Behaviors from Heterogeneous Agents","created":"2026-06-16","cited_by_count":0,"area":"offlinerl"},{"id":"2607.03248","title":"Unbiased Alignment for Large Language Models with Noisy Preferences","created":"2026-07-03","cited_by_count":0,"area":"alignment"},{"id":"2607.26358","title":"Post-Training at the Edge of Detectability: A Game-Theoretic Approach to Fine-Tuning","created":"2026-07-29","cited_by_count":0,"area":"lr"},{"id":"2608.14851","title":"Discovering High-Quality Chess Puzzles with Offline Reinforcement Learning","created":"2026-08-14","cited_by_count":0,"area":null},{"id":"2609.21432","title":"GVPO++: Group Variance Policy Optimization for LLM Post-Training and On-Policy Distillation","created":"2026-09-18","cited_by_count":0,"area":"lr"},{"id":"2609.23665","title":"Which Constraints Are Missing? Ask the Verifier: Graded Rewards for Constraint-Following Music Generation","created":"2026-09-20","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}],"next_cursor":"100"}