{"total":38,"rows":[{"id":"2112.11446","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","created":"2021-12-08","cited_by_count":1202,"area":null},{"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":"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":"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":"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":"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":"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":"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":"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":"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":"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":"2506.14723","title":"Adaptive Accompaniment with ReaLchords","created":"2025-06-17","cited_by_count":4,"area":null},{"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":"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":"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":"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":"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":"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":"2603.06138","title":"Partial Policy Gradients for RL in LLMs","created":"2026-03-06","cited_by_count":0,"area":null},{"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":"2609.34639","title":"Uniform Race: Parameter-Free Approximate Rejection Sampling","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}