{"total":17,"rows":[{"id":"2410.01679","title":"VinePPO: Refining Credit Assignment in RL Training of LLMs","created":"2024-10-02","cited_by_count":183,"area":null},{"id":"2310.17555","title":"Interactive Robot Learning from Verbal Correction","created":"2023-10-26","cited_by_count":29,"area":null},{"id":"2506.17188","title":"Towards AI Search Paradigm","created":"2025-06-20","cited_by_count":19,"area":null},{"id":"2310.11428","title":"Butterfly Effects of SGD Noise: Error Amplification in Behavior Cloning and Autoregression","created":"2023-10-17","cited_by_count":14,"area":null},{"id":"2411.14491","title":"A Survey on Human-Centric LLMs","created":"2024-11-20","cited_by_count":13,"area":null},{"id":"2407.12021","title":"Adaptive Draft-Verification for Efficient Large Language Model Decoding","created":"2024-06-27","cited_by_count":9,"area":null},{"id":"2402.03483","title":"SWAG: Storytelling With Action Guidance","created":"2024-02-05","cited_by_count":8,"area":null},{"id":"2504.09482","title":"HalluShift: Measuring Distribution Shifts towards Hallucination Detection in LLMs","created":"2025-04-13","cited_by_count":8,"area":null},{"id":"2505.13355","title":"Survey: Multi-Armed Bandits Meet Large Language Models","created":"2025-05-19","cited_by_count":7,"area":null},{"id":"2508.00719","title":"DAMR: Efficient and Adaptive Context-Aware Knowledge Graph Question Answering with LLM-Guided MCTS","created":"2025-08-01","cited_by_count":6,"area":null},{"id":"2505.21959","title":"EnsemW2S: Enhancing Weak-to-Strong Generalization with Large Language Model Ensembles","created":"2025-05-28","cited_by_count":4,"area":null},{"id":"2506.05387","title":"Advancing Decoding Strategies: Enhancements in Locally Typical Sampling for LLMs","created":"2025-06-03","cited_by_count":4,"area":null},{"id":"2408.03631","title":"Large Language Model as a Catalyst: A Paradigm Shift in Base Station Siting Optimization","created":"2024-08-07","cited_by_count":3,"area":null},{"id":"2508.00180","title":"EMA Without the Lag: Bias-Corrected Iterate Averaging Schemes","created":"2025-07-31","cited_by_count":3,"area":null},{"id":"2408.15658","title":"An Empirical Study on Self-correcting Large Language Models for Data Science Code Generation","created":"2024-08-28","cited_by_count":2,"area":null},{"id":"2409.02375","title":"How Privacy-Savvy Are Large Language Models? A Case Study on Compliance and Privacy Technical Review","created":"2024-09-04","cited_by_count":2,"area":null},{"id":"2410.04571","title":"EnsemW2S: Enhancing Weak-to-Strong Generalization with Large Language Model Ensembles","created":"2024-10-06","cited_by_count":1,"area":null}],"next_cursor":null}