{"total":80,"rows":[{"id":"2203.11147","title":"Teaching language models to support answers with verified quotes","created":"2022-03-21","cited_by_count":292,"area":null},{"id":"2109.10862","title":"Recursively Summarizing Books with Human Feedback","created":"2021-09-22","cited_by_count":290,"area":null},{"id":"2309.11235","title":"OpenChat: Advancing Open-source Language Models with Mixed-Quality Data","created":"2023-09-20","cited_by_count":252,"area":null},{"id":"2212.09611","title":"Optimizing Prompts for Text-to-Image Generation","created":"2022-12-19","cited_by_count":207,"area":null},{"id":"2305.11854","title":"Multimodal Web Navigation with Instruction-Finetuned Foundation Models","created":"2023-05-19","cited_by_count":160,"area":null},{"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":"2110.02034","title":"Dropout Q-Functions for Doubly Efficient Reinforcement Learning","created":"2021-10-05","cited_by_count":114,"area":null},{"id":"2202.08137","title":"A data-driven approach for learning to control computers","created":"2022-02-16","cited_by_count":88,"area":null},{"id":"2510.24684","title":"SPICE: Self-Play In Corpus Environments Improves Reasoning","created":"2025-10-28","cited_by_count":83,"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":"2204.08957","title":"COptiDICE: Offline Constrained Reinforcement Learning via Stationary Distribution Correction Estimation","created":"2022-04-19","cited_by_count":71,"area":null},{"id":"2211.05826","title":"The CRINGE Loss: Learning what language not to model","created":"2022-11-10","cited_by_count":39,"area":null},{"id":"2311.05584","title":"Zero-Shot Goal-Directed Dialogue via RL on Imagined Conversations","created":"2023-11-09","cited_by_count":38,"area":null},{"id":"2402.03659","title":"Learning to Generate Explainable Stock Predictions using Self-Reflective Large Language Models","created":"2024-02-06","cited_by_count":36,"area":null},{"id":"2108.01832","title":"Offline Decentralized Multi-Agent Reinforcement Learning","created":"2021-08-04","cited_by_count":33,"area":null},{"id":"2211.08714","title":"Reward Gaming in Conditional Text Generation","created":"2022-11-16","cited_by_count":30,"area":null},{"id":"2104.02293","title":"On the Optimality of Batch Policy Optimization Algorithms","created":"2021-04-06","cited_by_count":28,"area":null},{"id":"2110.04186","title":"Medical Dead-ends and Learning to Identify High-risk States and Treatments","created":"2021-10-08","cited_by_count":28,"area":null},{"id":"2310.20703","title":"Vanishing Gradients in Reinforcement Finetuning of Language Models","created":"2023-10-31","cited_by_count":27,"area":null},{"id":"2107.08966","title":"Decoupled Reinforcement Learning to Stabilise Intrinsically-Motivated Exploration","created":"2021-07-19","cited_by_count":25,"area":null},{"id":"2112.13521","title":"Can Reinforcement Learning Find Stackelberg-Nash Equilibria in General-Sum Markov Games with Myopic Followers?","created":"2021-12-27","cited_by_count":24,"area":null},{"id":"2209.13020","title":"Law Informs Code: A Legal Informatics Approach to Aligning Artificial Intelligence with Humans","created":"2022-09-14","cited_by_count":23,"area":null},{"id":"2204.10198","title":"Context-Aware Language Modeling for Goal-Oriented Dialogue Systems","created":"2022-04-18","cited_by_count":22,"area":null},{"id":"2404.18864","title":"Performance-Aligned LLMs for Generating Fast Code","created":"2024-04-29","cited_by_count":21,"area":null},{"id":"2206.05395","title":"Why is constrained neural language generation particularly challenging?","created":"2022-06-11","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":"2312.03631","title":"Mitigating Open-Vocabulary Caption Hallucinations","created":"2023-12-06","cited_by_count":19,"area":null},{"id":"2205.10671","title":"Pessimism for Offline Linear Contextual Bandits using $\\ell_p$ Confidence Sets","created":"2022-05-21","cited_by_count":18,"area":null},{"id":"2404.01954","title":"HyperCLOVA X Technical Report","created":"2024-04-02","cited_by_count":18,"area":null},{"id":"2101.00240","title":"A Survey on Deep Reinforcement Learning for Audio-Based Applications","created":"2021-01-01","cited_by_count":17,"area":null},{"id":"2102.10242","title":"Towards Automatic Evaluation of Dialog Systems: A Model-Free Off-Policy Evaluation Approach","created":"2021-02-20","cited_by_count":16,"area":null},{"id":"2401.04883","title":"Multi-User Chat Assistant (MUCA): a Framework Using LLMs to Facilitate Group Conversations","created":"2024-01-10","cited_by_count":14,"area":null},{"id":"2403.11574","title":"Offline Multitask Representation Learning for Reinforcement Learning","created":"2024-03-18","cited_by_count":14,"area":null},{"id":"2304.14177","title":"ChatGPT vs State-of-the-Art Models: A Benchmarking Study in Keyphrase Generation Task","created":"2023-04-27","cited_by_count":13,"area":null},{"id":"2212.10755","title":"JASMINE: Arabic GPT Models for Few-Shot Learning","created":"2022-12-21","cited_by_count":11,"area":null},{"id":"2308.14328","title":"Reinforcement Learning for Generative AI: A Survey","created":"2023-08-28","cited_by_count":11,"area":null},{"id":"2210.13623","title":"Reinforcement Learning and Bandits for Speech and Language Processing: Tutorial, Review and Outlook","created":"2022-10-24","cited_by_count":10,"area":null},{"id":"2304.04602","title":"Learning a Universal Human Prior for Dexterous Manipulation from Human Preference","created":"2023-04-10","cited_by_count":10,"area":null},{"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":"2208.02294","title":"Dynamic Planning in Open-Ended Dialogue using Reinforcement Learning","created":"2022-07-25","cited_by_count":8,"area":null},{"id":"2212.09750","title":"Human-in-the-loop Abstractive Dialogue Summarization","created":"2022-12-19","cited_by_count":8,"area":null},{"id":"2310.01041","title":"Language Model Decoding as Direct Metrics Optimization","created":"2023-10-02","cited_by_count":8,"area":null},{"id":"2209.15205","title":"ASPiRe:Adaptive Skill Priors for Reinforcement Learning","created":"2022-09-30","cited_by_count":7,"area":null},{"id":"2211.13743","title":"SkillS: Adaptive Skill Sequencing for Efficient Temporally-Extended Exploration","created":"2022-11-24","cited_by_count":6,"area":null},{"id":"2307.04274","title":"Assessing the efficacy of large language models in generating accurate teacher responses","created":"2023-07-09","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":"2502.07237","title":"DrugImproverGPT: A Large Language Model for Drug Optimization with Fine-Tuning via Structured Policy Optimization","created":"2025-02-11","cited_by_count":6,"area":null},{"id":"2103.06370","title":"Causal-aware Safe Policy Improvement for Task-oriented dialogue","created":"2021-03-10","cited_by_count":4,"area":null},{"id":"2310.06176","title":"Factual and Personalized Recommendations using Language Models and Reinforcement Learning","created":"2023-10-09","cited_by_count":4,"area":null},{"id":"2403.07933","title":"Corruption-Robust Offline Two-Player Zero-Sum Markov Games","created":"2024-03-04","cited_by_count":4,"area":null},{"id":"2410.15297","title":"Redefining Proactivity for Information Seeking Dialogue","created":"2024-10-20","cited_by_count":4,"area":null},{"id":"2106.11345","title":"Cogment: Open Source Framework For Distributed Multi-actor Training, Deployment & Operations","created":"2021-06-21","cited_by_count":3,"area":null},{"id":"2209.00876","title":"Dialogue Evaluation with Offline Reinforcement Learning","created":"2022-09-02","cited_by_count":3,"area":null},{"id":"2211.15355","title":"Causal Deep Reinforcement Learning Using Observational Data","created":"2022-11-28","cited_by_count":3,"area":null},{"id":"2307.13101","title":"Contrastive Example-Based Control","created":"2023-07-24","cited_by_count":3,"area":null},{"id":"2605.26552","title":"Aligning Few-Step Generative Models by Amortizing Sample-based Variational Inference","created":"2026-05-26","cited_by_count":3,"area":null},{"id":"2106.09973","title":"The Curse of Passive Data Collection in Batch Reinforcement Learning","created":"2021-06-18","cited_by_count":2,"area":null},{"id":"2108.06911","title":"Optimal Actor-Critic Policy with Optimized Training Datasets","created":"2021-08-16","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":"2209.07148","title":"Semi-supervised Batch Learning From Logged Data","created":"2022-09-15","cited_by_count":2,"area":null},{"id":"2209.07873","title":"Adaptive Natural Language Generation for Task-oriented Dialogue via Reinforcement Learning","created":"2022-09-16","cited_by_count":2,"area":null},{"id":"2311.04921","title":"Successor Features for Efficient Multisubject Controlled Text Generation","created":"2023-11-03","cited_by_count":2,"area":null},{"id":"2512.23087","title":"Dynamic Vocabulary Pruning: Stable LLM-RL by Taming the Tail","created":"2025-12-28","cited_by_count":2,"area":null},{"id":"2605.18580","title":"When Outcome Looks Right But Discipline Fails: Trace-Based Evaluation Under Hidden Competitor State","created":"2026-05-18","cited_by_count":2,"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":"2309.10413","title":"PICK: Polished & Informed Candidate Scoring for Knowledge-Grounded Dialogue Systems","created":"2023-09-19","cited_by_count":1,"area":null},{"id":"2312.05405","title":"Guaranteed Trust Region Optimization via Two-Phase KL Penalization","created":"2023-12-08","cited_by_count":1,"area":null},{"id":"2409.13299","title":"OMG-RL:Offline Model-based Guided Reward Learning for Heparin Treatment","created":"2024-09-20","cited_by_count":1,"area":null},{"id":"2409.15753","title":"Development and Validation of Heparin Dosing Policies Using an Offline Reinforcement Learning Algorithm","created":"2024-09-24","cited_by_count":1,"area":null},{"id":"2504.17277","title":"ExOSITO: Explainable Off-Policy Learning with Side Information for Intensive Care Unit Blood Test Orders","created":"2025-04-24","cited_by_count":1,"area":null},{"id":"2605.06529","title":"Market-Alignment Risk in Pricing Agents: Trace Diagnostics and Trace-Prior RL under Hidden Competitor State","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2606.09293","title":"One Model, Multiple Goals: Adaptive Multi-Objective Learning for E-commerce Dialogue Systems","created":"2026-06-08","cited_by_count":1,"area":null},{"id":"2112.06424","title":"A Benchmark for Low-Switching-Cost Reinforcement Learning","created":"2021-12-13","cited_by_count":0,"area":null},{"id":"2210.11111","title":"The Pump Scheduling Problem: A Real-World Scenario for Reinforcement Learning","created":"2022-10-20","cited_by_count":0,"area":null},{"id":"2304.00573","title":"Risk-Sensitive and Robust Model-Based Reinforcement Learning and Planning","created":"2023-04-02","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":"2507.10797","title":"Multi-Armed Sampling Problem and the End of Exploration","created":"2025-07-14","cited_by_count":0,"area":null},{"id":"2601.09261","title":"Learning to Trust Experience: A Monitor-Trust-Regulator Framework for Learning under Unobservable Feedback Reliability","created":"2026-01-14","cited_by_count":0,"area":null},{"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":"2605.29028","title":"Return-to-Go Is More Than a Number: Q-Guided Alignment for Return-Conditioned Supervised Learning","created":"2026-05-27","cited_by_count":0,"area":null}],"next_cursor":null}