{"total":21,"rows":[{"id":"2601.09195","title":"ProFit: Leveraging High-Value Signals in SFT via Probability-Guided Token Selection","created":"2026-01-14","cited_by_count":18,"area":null},{"id":"2506.01317","title":"T-SHIRT: Token-Selective Hierarchical Data Selection for Instruction Tuning","created":"2025-06-02","cited_by_count":13,"area":null},{"id":"2506.01790","title":"IF-GUIDE: Influence Function-Guided Detoxification of LLMs","created":"2025-06-02","cited_by_count":7,"area":null},{"id":"2505.20209","title":"Improving the OOD Performance of Closed-Source LLMs on NLI Through Strategic Data Selection","created":"2025-05-26","cited_by_count":4,"area":null},{"id":"2510.18250","title":"ssToken: Self-modulated and Semantic-aware Token Selection for LLM Fine-tuning","created":"2025-10-21","cited_by_count":3,"area":null},{"id":"2602.11424","title":"Gradients Must Earn Their Influence: Unifying SFT with Generalized Entropic Objectives","created":"2026-02-11","cited_by_count":3,"area":null},{"id":"2603.01185","title":"Token-level Data Selection for Safe LLM Fine-tuning","created":"2026-03-01","cited_by_count":3,"area":null},{"id":"2603.13985","title":"Supervised Fine-Tuning versus Reinforcement Learning: A Study of Post-Training Methods for Large Language Models","created":"2026-03-14","cited_by_count":3,"area":null},{"id":"2506.06991","title":"Evaluating LLM-Contaminated Crowdsourcing Data Without Ground Truth","created":"2025-06-08","cited_by_count":2,"area":null},{"id":"2602.14536","title":"Explainable Token-level Noise Filtering for LLM Fine-tuning Datasets","created":"2026-02-16","cited_by_count":1,"area":null},{"id":"2606.01635","title":"AlphaToken: Decoupling Adaptation and Stability for Path-Aware Response Token Valuation in LLM Post-Training","created":"2026-06-01","cited_by_count":1,"area":null},{"id":"2606.18286","title":"CODEBLOCK: Learning to Supervise Code at the Right Granularity","created":"2026-06-10","cited_by_count":1,"area":null},{"id":"2506.16731","title":"Incentivizing High-quality Participation From Federated Learning Agents","created":"2025-06-20","cited_by_count":0,"area":null},{"id":"2512.10821","title":"Agile Deliberation: Concept Deliberation for Subjective Visual Classification","created":"2025-12-11","cited_by_count":0,"area":null},{"id":"2602.01227","title":"Supervised Fine-Tuning Needs to Unlock the Potential of Token Priority","created":"2026-02-01","cited_by_count":0,"area":null},{"id":"2605.06166","title":"One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.09404","title":"Let the Target Select for Itself: Data Selection via Target-Aligned Paths","created":"2026-05-10","cited_by_count":0,"area":null},{"id":"2605.09665","title":"Learning Multi-Indicator Weights for Data Selection: A Joint Task-Model Adaptation Framework with Efficient Proxies","created":"2026-05-10","cited_by_count":0,"area":null},{"id":"2606.10706","title":"Unifying Data, Memory, and Compute Efficiency in LLM training: A Survey","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2609.22943","title":"Token Utility Is Selection-Conditioned: Coupled Selection of Prompt Context and Response Supervision for Instruction Tuning","created":"2026-09-19","cited_by_count":0,"area":null},{"id":"2609.33405","title":"Decoupling Token Roles in Autoregressive Pretraining","created":"2026-09-27","cited_by_count":0,"area":null}],"next_cursor":null}