{"total":24,"rows":[{"id":"2404.14367","title":"Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data","created":"2024-04-22","cited_by_count":185,"area":null},{"id":"2410.20290","title":"Fast Best-of-N Decoding via Speculative Rejection","created":"2024-10-26","cited_by_count":112,"area":null},{"id":"2508.19229","title":"StepWiser: Stepwise Generative Judges for Wiser Reasoning","created":"2025-08-26","cited_by_count":28,"area":null},{"id":"2502.19110","title":"Conformal Linguistic Calibration: Trading-off between Factuality and Specificity","created":"2025-02-26","cited_by_count":20,"area":null},{"id":"2407.12164","title":"Subject-driven Text-to-Image Generation via Preference-based Reinforcement Learning","created":"2024-07-16","cited_by_count":12,"area":null},{"id":"2502.11541","title":"MuSC: Improving Complex Instruction Following with Multi-granularity Self-Contrastive Training","created":"2025-02-17","cited_by_count":12,"area":null},{"id":"2410.22296","title":"Generalists vs. Specialists: Evaluating LLMs on Highly-Constrained Biophysical Sequence Optimization Tasks","created":"2024-10-29","cited_by_count":10,"area":null},{"id":"2412.14656","title":"Length Controlled Generation for Black-box LLMs","created":"2024-12-19","cited_by_count":8,"area":null},{"id":"2505.23829","title":"BiasFilter: An Inference-Time Debiasing Framework for Large Language Models","created":"2025-05-28","cited_by_count":6,"area":null},{"id":"2504.07527","title":"Supervised Optimism Correction: Be Confident When LLMs Are Sure","created":"2025-04-10","cited_by_count":5,"area":null},{"id":"2505.20218","title":"Fine-grained List-wise Alignment for Generative Medication Recommendation","created":"2025-05-26","cited_by_count":5,"area":null},{"id":"2603.23550","title":"Implicit Turn-Wise Policy Optimization for Proactive User-LLM Interaction","created":"2026-03-21","cited_by_count":4,"area":null},{"id":"2605.02141","title":"On the Optimal Sample Complexity of Offline Multi-Armed Bandits with KL Regularization","created":"2026-05-04","cited_by_count":4,"area":null},{"id":"2502.10505","title":"Preference learning made easy: Everything should be understood through win rate","created":"2025-02-14","cited_by_count":3,"area":null},{"id":"2505.11081","title":"ShiQ: Bringing back Bellman to LLMs","created":"2025-05-16","cited_by_count":3,"area":null},{"id":"2412.19005","title":"Enhancing Audiovisual Speech Recognition through Bifocal Preference Optimization","created":"2024-12-26","cited_by_count":1,"area":null},{"id":"2506.12527","title":"Detection, Classification, and Mitigation of Gender Bias in Large Language Models","created":"2025-06-14","cited_by_count":1,"area":null},{"id":"2510.14106","title":"Generating Fair Consensus Statements with Social Choice on Token-Level MDPs","created":"2025-10-15","cited_by_count":1,"area":null},{"id":"2603.00963","title":"Stabilizing Policy Optimization via Logits Convexity","created":"2026-03-01","cited_by_count":1,"area":null},{"id":"2412.20382","title":"Natural Language Fine-Tuning","created":"2024-12-29","cited_by_count":0,"area":null},{"id":"2507.12260","title":"Translationese-index: Using Likelihood Ratios for Graded and Generalizable Measurement of Translationese","created":"2025-07-16","cited_by_count":0,"area":null},{"id":"2511.22169","title":"Real-Time Long Horizon Air Quality Forecasting via Group-Relative Policy Optimization","created":"2025-11-27","cited_by_count":0,"area":null},{"id":"2604.02349","title":"OPRIDE: Offline Preference-based Reinforcement Learning via In-Dataset Exploration","created":"2026-02-19","cited_by_count":0,"area":null},{"id":"2608.07419","title":"Beyond Post-Hoc Temperature Scaling: Bilevel Optimization for LLM Calibration","created":"2026-08-07","cited_by_count":0,"area":null}],"next_cursor":null}