{"total":33,"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":"2303.04129","title":"Foundation Models for Decision Making: Problems, Methods, and Opportunities","created":"2023-03-07","cited_by_count":164,"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":"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":"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":"2104.02726","title":"Creativity and Machine Learning: A Survey","created":"2021-04-06","cited_by_count":21,"area":null},{"id":"2312.03631","title":"Mitigating Open-Vocabulary Caption Hallucinations","created":"2023-12-06","cited_by_count":19,"area":null},{"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":"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":"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":"2308.09970","title":"Tackling Vision Language Tasks Through Learning Inner Monologues","created":"2023-08-19","cited_by_count":7,"area":null},{"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":"2506.14723","title":"Adaptive Accompaniment with ReaLchords","created":"2025-06-17","cited_by_count":4,"area":null},{"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":"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":"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":"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":"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":"2608.14851","title":"Discovering High-Quality Chess Puzzles with Offline Reinforcement Learning","created":"2026-08-14","cited_by_count":0,"area":null},{"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":"2609.34639","title":"Uniform Race: Parameter-Free Approximate Rejection Sampling","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}