{"total":40,"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":"2202.06935","title":"Repairing the Cracked Foundation: A Survey of Obstacles in Evaluation Practices for Generated Text","created":"2022-02-14","cited_by_count":155,"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":"2109.00486","title":"Survey of Low-Resource Machine Translation","created":"2021-09-01","cited_by_count":92,"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":"2306.12420","title":"LMFlow: An Extensible Toolkit for Finetuning and Inference of Large Foundation Models","created":"2023-06-21","cited_by_count":60,"area":null},{"id":"2104.05336","title":"Machine Translation Decoding beyond Beam Search","created":"2021-04-12","cited_by_count":55,"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":"2509.24372","title":"Evolution Strategies at Scale: LLM Fine-Tuning Beyond Reinforcement Learning","created":"2025-09-29","cited_by_count":34,"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":"2302.13344","title":"Tailoring Language Generation Models under Total Variation Distance","created":"2023-02-26","cited_by_count":27,"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":"2109.00527","title":"Boosting Search Engines with Interactive Agents","created":"2021-09-01","cited_by_count":19,"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":"2308.02223","title":"ESRL: Efficient Sampling-based Reinforcement Learning for Sequence Generation","created":"2023-08-04","cited_by_count":15,"area":null},{"id":"2104.07541","title":"Reward Optimization for Neural Machine Translation with Learned Metrics","created":"2021-04-15","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":"2410.20749","title":"Matryoshka Pilot: Learning to Drive Black-Box LLMs with LLMs","created":"2024-10-28","cited_by_count":9,"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":"2112.08670","title":"Amortized Noisy Channel Neural Machine Translation","created":"2021-12-16","cited_by_count":4,"area":null},{"id":"2206.13974","title":"Joint Generator-Ranker Learning for Natural Language Generation","created":"2022-06-28","cited_by_count":4,"area":null},{"id":"2212.03230","title":"Switching to Discriminative Image Captioning by Relieving a Bottleneck of Reinforcement Learning","created":"2022-12-06","cited_by_count":4,"area":null},{"id":"2109.09371","title":"Learning Natural Language Generation from Scratch","created":"2021-09-20","cited_by_count":2,"area":null},{"id":"2201.08810","title":"GAP-Gen: Guided Automatic Python Code Generation","created":"2022-01-19","cited_by_count":2,"area":null},{"id":"2206.01011","title":"Policy Gradient Algorithms with Monte Carlo Tree Learning for Non-Markov Decision Processes","created":"2022-06-02","cited_by_count":2,"area":null},{"id":"2210.03053","title":"Reinforcement Learning with Large Action Spaces for Neural Machine Translation","created":"2022-10-06","cited_by_count":2,"area":null},{"id":"2402.13936","title":"Distinctive Image Captioning: Leveraging Ground Truth Captions in CLIP Guided Reinforcement Learning","created":"2024-02-21","cited_by_count":2,"area":null},{"id":"2101.12640","title":"Enhancing the Transformer Decoder with Transition-based Syntax","created":"2021-01-29","cited_by_count":1,"area":null},{"id":"2102.11403","title":"Exploring Supervised and Unsupervised Rewards in Machine Translation","created":"2021-02-22","cited_by_count":1,"area":null},{"id":"2207.11161","title":"Lagrangian Method for Q-Function Learning (with Applications to Machine Translation)","created":"2022-07-22","cited_by_count":1,"area":null},{"id":"2209.14694","title":"GROOT: Corrective Reward Optimization for Generative Sequential Labeling","created":"2022-09-29","cited_by_count":1,"area":null},{"id":"2305.13667","title":"Optimizing Non-Autoregressive Transformers with Contrastive Learning","created":"2023-05-23","cited_by_count":1,"area":null},{"id":"2603.17952","title":"Gender Disambiguation in Machine Translation: Diagnostic Evaluation in Decoder-Only Architectures","created":"2026-03-18","cited_by_count":1,"area":null},{"id":"2109.13097","title":"Towards Reinforcement Learning for Pivot-based Neural Machine Translation with Non-autoregressive Transformer","created":"2021-09-27","cited_by_count":0,"area":null},{"id":"2211.16550","title":"Soft Alignment Objectives for Robust Adaptation of Language Generation","created":"2022-11-29","cited_by_count":0,"area":null},{"id":"2407.06990","title":"Segment-Based Interactive Machine Translation for Pre-trained Models","created":"2024-07-09","cited_by_count":0,"area":null},{"id":"2602.02258","title":"Alignment-Aware Model Adaptation via Feedback-Guided Optimization","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2603.19152","title":"VEPO: Variable Entropy Policy Optimization for Low-Resource Language Foundation Models","created":"2026-03-19","cited_by_count":0,"area":null}],"next_cursor":null}