{"total":32,"rows":[{"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":"2309.00779","title":"Value Kaleidoscope: Engaging AI with Pluralistic Human Values, Rights, and Duties","created":"2023-09-02","cited_by_count":97,"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":"2306.11816","title":"Learning to Generate Better Than Your LLM","created":"2023-06-20","cited_by_count":49,"area":null},{"id":"2212.10938","title":"Critic-Guided Decoding for Controlled Text Generation","created":"2022-12-21","cited_by_count":45,"area":null},{"id":"2106.08942","title":"Revisiting the Weaknesses of Reinforcement Learning for Neural Machine Translation","created":"2021-06-16","cited_by_count":33,"area":null},{"id":"2305.15065","title":"Inference-Time Policy Adapters (IPA): Tailoring Extreme-Scale LMs without Fine-tuning","created":"2023-05-24","cited_by_count":33,"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":"2102.07024","title":"Interactive Learning from Activity Description","created":"2021-02-13","cited_by_count":26,"area":null},{"id":"2105.02590","title":"Reliability Testing for Natural Language Processing Systems","created":"2021-05-06","cited_by_count":25,"area":null},{"id":"2212.09710","title":"Continual Learning for Instruction Following from Realtime Feedback","created":"2022-12-19","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":"2106.03816","title":"Diversity driven Query Rewriting in Search Advertising","created":"2021-06-07","cited_by_count":15,"area":null},{"id":"2308.02223","title":"ESRL: Efficient Sampling-based Reinforcement Learning for Sequence Generation","created":"2023-08-04","cited_by_count":15,"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":"2311.07167","title":"STEER: Unified Style Transfer with Expert Reinforcement","created":"2023-11-13","cited_by_count":14,"area":null},{"id":"2305.12473","title":"Continually Improving Extractive QA via Human Feedback","created":"2023-05-21","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":"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":"2105.13385","title":"Online Learning Meets Machine Translation Evaluation: Finding the Best Systems with the Least Human Effort","created":"2021-05-27","cited_by_count":7,"area":null},{"id":"2207.08583","title":"MAD for Robust Reinforcement Learning in Machine Translation","created":"2022-07-18","cited_by_count":7,"area":null},{"id":"2307.05538","title":"Advancements in Scientific Controllable Text Generation Methods","created":"2023-07-08","cited_by_count":7,"area":null},{"id":"2306.06779","title":"Multi-Source Test-Time Adaptation as Dueling Bandits for Extractive Question Answering","created":"2023-06-11","cited_by_count":6,"area":null},{"id":"2407.01490","title":"LLM See, LLM Do: Guiding Data Generation to Target Non-Differentiable Objectives","created":"2024-07-01","cited_by_count":6,"area":null},{"id":"2203.04507","title":"Onception: Active Learning with Expert Advice for Real World Machine Translation","created":"2022-03-09","cited_by_count":5,"area":null},{"id":"2203.12048","title":"Review of Metrics to Measure the Stability, Robustness and Resilience of Reinforcement Learning","created":"2022-03-22","cited_by_count":2,"area":null},{"id":"2403.00141","title":"EROS: Entity-Driven Controlled Policy Document Summarization","created":"2024-02-29","cited_by_count":2,"area":null},{"id":"2603.17145","title":"REAL: Regression-Aware Reinforcement Learning for LLM-as-a-Judge","created":"2026-03-17","cited_by_count":2,"area":null},{"id":"2104.05224","title":"Estimating Subjective Crowd-Evaluations as an Additional Objective to Improve Natural Language Generation","created":"2021-04-12","cited_by_count":0,"area":null},{"id":"2301.00688","title":"Active Learning for Neural Machine Translation","created":"2022-12-30","cited_by_count":0,"area":null},{"id":"2505.15069","title":"In-Domain African Languages Translation Using LLMs and Multi-armed Bandits","created":"2025-05-21","cited_by_count":0,"area":null}],"next_cursor":null}