{"total":93,"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":"2112.11446","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","created":"2021-12-08","cited_by_count":1202,"area":null},{"id":"2102.08363","title":"COMBO: Conservative Offline Model-Based Policy Optimization","created":"2021-02-16","cited_by_count":370,"area":"offlinerl"},{"id":"2302.08582","title":"Pretraining Language Models with Human Preferences","created":"2023-02-16","cited_by_count":247,"area":"alignment"},{"id":"2210.01241","title":"Is Reinforcement Learning (Not) for Natural Language Processing: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimization","created":"2022-10-03","cited_by_count":246,"area":null},{"id":"2402.19446","title":"ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL","created":"2024-02-29","cited_by_count":228,"area":"agents"},{"id":"2210.13312","title":"Neural Theory-of-Mind? On the Limits of Social Intelligence in Large LMs","created":"2022-10-24","cited_by_count":220,"area":"wm"},{"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":"2105.04387","title":"Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Survey","created":"2021-05-10","cited_by_count":130,"area":null},{"id":"2111.10364","title":"Generalized Decision Transformer for Offline Hindsight Information Matching","created":"2021-11-19","cited_by_count":106,"area":"offlinerl"},{"id":"2204.05618","title":"When Should We Prefer Offline Reinforcement Learning Over Behavioral Cloning?","created":"2022-04-12","cited_by_count":89,"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":"2303.05453","title":"Personalisation within bounds: A risk taxonomy and policy framework for the alignment of large language models with personalised feedback","created":"2023-03-09","cited_by_count":87,"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":"2201.12122","title":"Can Wikipedia Help Offline Reinforcement Learning?","created":"2022-01-28","cited_by_count":77,"area":"offlinerl"},{"id":"2305.18438","title":"Reinforcement Learning with Human Feedback: Learning Dynamic Choices via Pessimism","created":"2023-05-29","cited_by_count":69,"area":"alignment"},{"id":"2109.08128","title":"Conservative Data Sharing for Multi-Task Offline Reinforcement Learning","created":"2021-09-16","cited_by_count":64,"area":"offlinerl"},{"id":"2402.08265","title":"A Dense Reward View on Aligning Text-to-Image Diffusion with Preference","created":"2024-02-13","cited_by_count":55,"area":"diffusion"},{"id":"2310.07629","title":"The Past, Present and Better Future of Feedback Learning in Large Language Models for Subjective Human Preferences and Values","created":"2023-10-11","cited_by_count":54,"area":"alignment"},{"id":"2112.07544","title":"Modeling Strong and Human-Like Gameplay with KL-Regularized Search","created":"2021-12-14","cited_by_count":50,"area":"offlinerl"},{"id":"2410.09008","title":"SuperCorrect: Advancing Small LLM Reasoning with Thought Template Distillation and Self-Correction","created":"2024-10-11","cited_by_count":40,"area":"lr"},{"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":"2209.08025","title":"Trustworthy Reinforcement Learning Against Intrinsic Vulnerabilities: Robustness, Safety, and Generalizability","created":"2022-09-16","cited_by_count":36,"area":null},{"id":"2402.02439","title":"DiffStitch: Boosting Offline Reinforcement Learning with Diffusion-based Trajectory Stitching","created":"2024-02-04","cited_by_count":36,"area":"offlinerl"},{"id":"2305.17878","title":"Ask an Expert: Leveraging Language Models to Improve Strategic Reasoning in Goal-Oriented Dialogue Models","created":"2023-05-29","cited_by_count":31,"area":"lr"},{"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":"2110.07395","title":"Offline Reinforcement Learning with Soft Behavior Regularization","created":"2021-10-14","cited_by_count":28,"area":"offlinerl"},{"id":"2310.05782","title":"Aligning Language Models with Human Preferences via a Bayesian Approach","created":"2023-10-09","cited_by_count":27,"area":"alignment"},{"id":"2312.05742","title":"The Generalization Gap in Offline Reinforcement Learning","created":"2023-12-10","cited_by_count":26,"area":"offlinerl"},{"id":"2312.07401","title":"On Diversified Preferences of Large Language Model Alignment","created":"2023-12-12","cited_by_count":26,"area":"alignment"},{"id":"2404.11023","title":"Advancing Social Intelligence in AI Agents: Technical Challenges and Open Questions","created":"2024-04-17","cited_by_count":22,"area":null},{"id":"2211.11096","title":"Let Offline RL Flow: Training Conservative Agents in the Latent Space of Normalizing Flows","created":"2022-11-20","cited_by_count":21,"area":"offlinerl"},{"id":"2108.04812","title":"Continual Learning for Grounded Instruction Generation by Observing Human Following Behavior","created":"2021-08-10","cited_by_count":19,"area":null},{"id":"2302.10342","title":"Fantastic Rewards and How to Tame Them: A Case Study on Reward Learning for Task-oriented Dialogue Systems","created":"2023-02-20","cited_by_count":19,"area":null},{"id":"2406.10278","title":"Prompt-Based Length Controlled Generation with Multiple Control Types","created":"2024-06-12","cited_by_count":19,"area":null},{"id":"2411.01493","title":"Sample-Efficient Alignment for LLMs","created":"2024-11-03","cited_by_count":16,"area":"alignment"},{"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":"2203.10079","title":"Simulating Bandit Learning from User Feedback for Extractive Question Answering","created":"2022-03-18","cited_by_count":14,"area":null},{"id":"2308.12030","title":"Prompt-Based Length Controlled Generation with Reinforcement Learning","created":"2023-08-23","cited_by_count":14,"area":null},{"id":"2310.10735","title":"Building Persona Consistent Dialogue Agents with Offline Reinforcement Learning","created":"2023-10-16","cited_by_count":14,"area":null},{"id":"2509.25137","title":"The Era of Real-World Human Interaction: RL from User Conversations","created":"2025-09-29","cited_by_count":13,"area":null},{"id":"2204.03084","title":"Knowledge Infused Decoding","created":"2022-04-06","cited_by_count":12,"area":null},{"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":"2110.04686","title":"Braxlines: Fast and Interactive Toolkit for RL-driven Behavior Engineering beyond Reward Maximization","created":"2021-10-10","cited_by_count":11,"area":null},{"id":"2208.14165","title":"Towards Boosting the Open-Domain Chatbot with Human Feedback","created":"2022-08-30","cited_by_count":11,"area":"alignment"},{"id":"2305.12473","title":"Continually Improving Extractive QA via Human Feedback","created":"2023-05-21","cited_by_count":11,"area":null},{"id":"2408.07461","title":"Problem Solving Through Human-AI Preference-Based Cooperation","created":"2024-08-14","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":"2506.06964","title":"Offline RL by Reward-Weighted Fine-Tuning for Conversation Optimization","created":"2025-06-08","cited_by_count":10,"area":"alignment"},{"id":"2211.16773","title":"KRLS: Improving End-to-End Response Generation in Task Oriented Dialog with Reinforced Keywords Learning","created":"2022-11-30","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":"2208.02294","title":"Dynamic Planning in Open-Ended Dialogue using Reinforcement Learning","created":"2022-07-25","cited_by_count":8,"area":null},{"id":"2105.11197","title":"Towards Standard Criteria for human evaluation of Chatbots: A Survey","created":"2021-05-24","cited_by_count":6,"area":null},{"id":"2307.12425","title":"On the Effectiveness of Offline RL for Dialogue Response Generation","created":"2023-07-23","cited_by_count":6,"area":null},{"id":"2603.03192","title":"MoD-DPO: Towards Mitigating Cross-modal Hallucinations in Omni LLMs using Modality Decoupled Preference Optimization","created":"2026-03-03","cited_by_count":6,"area":"alignment"},{"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":"2506.14723","title":"Adaptive Accompaniment with ReaLchords","created":"2025-06-17","cited_by_count":4,"area":null},{"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":"2111.14346","title":"Pessimistic Model Selection for Offline Deep Reinforcement Learning","created":"2021-11-29","cited_by_count":3,"area":"offlinerl"},{"id":"2306.08364","title":"Provably Efficient Offline Reinforcement Learning with Perturbed Data Sources","created":"2023-06-14","cited_by_count":3,"area":"offlinerl"},{"id":"2310.15594","title":"Retrieval-based Knowledge Transfer: An Effective Approach for Extreme Large Language Model Compression","created":"2023-10-24","cited_by_count":3,"area":null},{"id":"2509.19305","title":"Wavelet Fourier Diffuser: Frequency-Aware Diffusion Model for Reinforcement Learning","created":"2025-09-04","cited_by_count":3,"area":"diffusion"},{"id":"2509.25810","title":"Learning to Reason as Action Abstractions with Scalable Mid-Training RL","created":"2025-09-30","cited_by_count":3,"area":"lr"},{"id":"2511.21638","title":"Iterative GRPO: Batch-Online Multi-Turn RL via Single-Turn RLHF","created":"2025-11-26","cited_by_count":3,"area":"lr"},{"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":"2104.08231","title":"An Adversarially-Learned Turing Test for Dialog Generation Models","created":"2021-04-16","cited_by_count":2,"area":null},{"id":"2109.09371","title":"Learning Natural Language Generation from Scratch","created":"2021-09-20","cited_by_count":2,"area":null},{"id":"2410.15714","title":"Offline reinforcement learning for job-shop scheduling problems","created":"2024-10-21","cited_by_count":2,"area":"offlinerl"},{"id":"2505.15922","title":"Aligning Dialogue Agents with Global Feedback via Large Language Model Multimodal Reward Decomposition","created":"2025-05-21","cited_by_count":2,"area":"agents"},{"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":"2212.10515","title":"CausalDialogue: Modeling Utterance-level Causality in Conversations","created":"2022-12-20","cited_by_count":1,"area":null},{"id":"2303.13465","title":"Deep RL with Hierarchical Action Exploration for Dialogue Generation","created":"2023-03-22","cited_by_count":1,"area":null},{"id":"2402.02772","title":"Contrastive Diffuser: Planning Towards High Return States via Contrastive Learning","created":"2024-02-05","cited_by_count":1,"area":"offlinerl"},{"id":"2403.11330","title":"Improving Dialogue Agents by Decomposing One Global Explicit Annotation with Local Implicit Multimodal Feedback","created":"2024-03-17","cited_by_count":1,"area":"agents"},{"id":"2404.10393","title":"Offline Trajectory Optimization for Offline Reinforcement Learning","created":"2024-04-16","cited_by_count":1,"area":"offlinerl"},{"id":"2408.16751","title":"A Gradient Analysis Framework for Rewarding Good and Penalizing Bad Examples in Language Models","created":"2024-08-29","cited_by_count":1,"area":"alignment"},{"id":"2504.02646","title":"Prompt Optimization with Logged Bandit Data","created":"2025-04-03","cited_by_count":1,"area":null},{"id":"2506.01524","title":"V-VAE: A Variational Auto Encoding Framework Towards Fine-Grained Control over Human-Like Chat","created":"2025-06-02","cited_by_count":1,"area":null},{"id":"2601.20198","title":"DeRaDiff: Denoising Time Realignment of Diffusion Models","created":"2026-01-28","cited_by_count":1,"area":"diffusion"},{"id":"2603.01973","title":"CharacterFlywheel: Scaling Iterative Improvement of Engaging and Steerable LLMs in Production","created":"2026-03-02","cited_by_count":1,"area":null},{"id":"2302.13505","title":"Multi-Action Dialog Policy Learning from Logged User Feedback","created":"2023-02-27","cited_by_count":0,"area":null},{"id":"2310.10556","title":"Sample Complexity of Preference-Based Nonparametric Off-Policy Evaluation with Deep Networks","created":"2023-10-16","cited_by_count":0,"area":"alignment"},{"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":"2507.21274","title":"Large Language Model-Enhanced Reinforcement Learning for Diverse and Novel Recommendations","created":"2025-07-28","cited_by_count":0,"area":null},{"id":"2512.20169","title":"Learning to Reason in LLMs by Expectation Maximization","created":"2025-12-23","cited_by_count":0,"area":"lr"},{"id":"2603.06138","title":"Partial Policy Gradients for RL in LLMs","created":"2026-03-06","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":"2605.09268","title":"Beyond Continuity: Challenges of Context Switching in Multi-Turn Dialogue with LLMs","created":"2026-05-10","cited_by_count":0,"area":null},{"id":"2607.03248","title":"Unbiased Alignment for Large Language Models with Noisy Preferences","created":"2026-07-03","cited_by_count":0,"area":"alignment"},{"id":"2608.21969","title":"ToSCA: Leveraging Hierarchical Reinforcement Learning on Temporal and Strategic Abstractions of Conversational Agents","created":"2026-08-22","cited_by_count":0,"area":"alignment"},{"id":"2609.34639","title":"Uniform Race: Parameter-Free Approximate Rejection Sampling","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.14976","title":"Metric-Driven Reinforcement Learning for Object Hallucination Reduction in LVLM-Based Image Captioning","created":"2026-10-10","cited_by_count":0,"area":"mllm"}],"next_cursor":null}