{"total":19,"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":"2403.06963","title":"The pitfalls of next-token prediction","created":"2024-03-11","cited_by_count":160,"area":null},{"id":"2406.16838","title":"From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Models","created":"2024-06-24","cited_by_count":137,"area":null},{"id":"2206.01626","title":"Reincarnating Reinforcement Learning: Reusing Prior Computation to Accelerate Progress","created":"2022-06-03","cited_by_count":65,"area":null},{"id":"2306.11816","title":"Learning to Generate Better Than Your LLM","created":"2023-06-20","cited_by_count":49,"area":null},{"id":"2210.14698","title":"Autoregressive Structured Prediction with Language Models","created":"2022-10-26","cited_by_count":43,"area":null},{"id":"2203.09486","title":"An Imitation Learning Curriculum for Text Editing with Non-Autoregressive Models","created":"2022-03-17","cited_by_count":20,"area":null},{"id":"2203.10452","title":"CrossBeam: Learning to Search in Bottom-Up Program Synthesis","created":"2022-03-20","cited_by_count":18,"area":null},{"id":"2210.06600","title":"Iterative Document-level Information Extraction via Imitation Learning","created":"2022-10-12","cited_by_count":11,"area":null},{"id":"2210.08708","title":"Teacher Forcing Recovers Reward Functions for Text Generation","created":"2022-10-17","cited_by_count":11,"area":null},{"id":"2111.06257","title":"Branch and Bound in Mixed Integer Linear Programming Problems: A Survey of Techniques and Trends","created":"2021-11-05","cited_by_count":9,"area":null},{"id":"2102.02574","title":"Incremental Beam Manipulation for Natural Language Generation","created":"2021-02-04","cited_by_count":6,"area":null},{"id":"2306.02049","title":"LambdaBeam: Neural Program Search with Higher-Order Functions and Lambdas","created":"2023-06-03","cited_by_count":6,"area":null},{"id":"2211.15068","title":"Learning to design without prior data: Discovering generalizable design strategies using deep learning and tree search","created":"2022-11-28","cited_by_count":5,"area":null},{"id":"2105.09404","title":"Computational Morphology with Neural Network Approaches","created":"2021-05-19","cited_by_count":2,"area":null},{"id":"2109.06308","title":"Improving Scheduled Sampling with Elastic Weight Consolidation for Neural Machine Translation","created":"2021-09-13","cited_by_count":1,"area":null},{"id":"2405.11819","title":"Beyond MLE: Investigating SEARNN for Low-Resourced Neural Machine Translation","created":"2024-05-20","cited_by_count":0,"area":null},{"id":"2406.09393","title":"Improving Autoregressive Training with Dynamic Oracles","created":"2024-06-13","cited_by_count":0,"area":null},{"id":"2609.14299","title":"Learning Source Acquisition Policies by Offline Planning","created":"2026-09-13","cited_by_count":0,"area":null}],"next_cursor":null}