{"total":17,"rows":[{"id":"2405.14394","title":"Instruction Tuning With Loss Over Instructions","created":"2024-05-23","cited_by_count":40,"area":null},{"id":"2503.13975","title":"Navigating Rifts in Human-LLM Grounding: Study and Benchmark","created":"2025-03-18","cited_by_count":29,"area":null},{"id":"2408.08661","title":"MIA-Tuner: Adapting Large Language Models as Pre-training Text Detector","created":"2024-08-16","cited_by_count":15,"area":null},{"id":"2509.21826","title":"ResT: Reshaping Token-Level Policy Gradients for Tool-Use Large Language Models","created":"2025-09-26","cited_by_count":10,"area":null},{"id":"2603.18534","title":"Data-efficient pre-training by scaling synthetic megadocs","created":"2026-03-19","cited_by_count":7,"area":null},{"id":"2411.09539","title":"Fine-tuning Large Language Models with Limited Data: A Survey and Practical Guide","created":"2024-11-14","cited_by_count":4,"area":null},{"id":"2510.14113","title":"Toward Cybersecurity-Expert Small Language Models","created":"2025-10-15","cited_by_count":4,"area":null},{"id":"2503.03607","title":"Psy-Insight: Explainable Multi-turn Bilingual Dataset for Mental Health Counseling","created":"2025-03-05","cited_by_count":3,"area":null},{"id":"2601.13969","title":"Autonomous Knowledge Graph Exploration with Adaptive Breadth-Depth Retrieval","created":"2026-01-20","cited_by_count":3,"area":null},{"id":"2510.00662","title":"Facilitating Cognitive Accessibility with LLMs: A Multi-Task Approach to Easy-to-Read Text Generation","created":"2025-10-01","cited_by_count":2,"area":null},{"id":"2603.05776","title":"PVminerLLM: Structured Extraction of Patient Voice from Patient-Generated Text using Large Language Models","created":"2026-03-06","cited_by_count":2,"area":null},{"id":"2509.00921","title":"Supervised In-Context Fine-Tuning for Generative Sequence Labeling","created":"2025-08-31","cited_by_count":1,"area":null},{"id":"2409.13749","title":"KodeXv0.1: A Family of State-of-the-Art Financial Large Language Models","created":"2024-09-13","cited_by_count":0,"area":null},{"id":"2601.23206","title":"High-quality generation of dynamic game content via small language models: A proof of concept","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2606.19528","title":"Techniques for Peak Memory Reduction for LoRA Fine-tuning of LLMs on Edge Devices","created":"2026-06-17","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}