{"total":15,"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":"2410.15956","title":"Do Large Language Models Have an English Accent? Evaluating and Improving the Naturalness of Multilingual LLMs","created":"2024-10-21","cited_by_count":19,"area":null},{"id":"2602.04863","title":"Subliminal Effects in Your Data: A General Mechanism via Log-Linearity","created":"2026-02-04","cited_by_count":19,"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":"2506.03483","title":"APT: Improving Specialist LLM Performance with Weakness Case Acquisition and Iterative Preference Training","created":"2025-06-04","cited_by_count":12,"area":null},{"id":"2503.04736","title":"Standardizing Intelligence: Aligning Generative AI for Regulatory and Operational Compliance","created":"2025-02-03","cited_by_count":5,"area":null},{"id":"2604.03058","title":"Verbalizing LLMs' assumptions to explain and control sycophancy","created":"2026-04-03","cited_by_count":5,"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":"2503.22764","title":"Boosting Large Language Models with Mask Fine-Tuning","created":"2025-03-27","cited_by_count":3,"area":null},{"id":"2510.03528","title":"Fine-Tuning on Noisy Instructions: Effects on Generalization and Performance","created":"2025-10-03","cited_by_count":2,"area":null},{"id":"2410.02465","title":"Revealing the Inherent Instructability of Pre-Trained Language Models","created":"2024-10-03","cited_by_count":0,"area":null},{"id":"2506.23979","title":"TaP: A Taxonomy-Guided Framework for Automated and Scalable Preference Data Generation","created":"2025-06-30","cited_by_count":0,"area":null},{"id":"2601.21618","title":"Semantic Content Determines Algorithmic Performance","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2603.21438","title":"PROMPT2BOX:Improving LLM Weakness Discovery and Specificity Estimation by Uncovering Entailment Structure among Prompts","created":"2026-03-22","cited_by_count":0,"area":null},{"id":"2609.01573","title":"Scaling Near-Optimal SFT-RL Annotation Budget Allocation from Small to Large LLMs","created":"2026-09-01","cited_by_count":0,"area":null}],"next_cursor":null}