SATQuest: A Verifier for Logical Reasoning Evaluation and Reinforcement Fine-Tuning of LLMs
SATQuest:用于大语言模型逻辑推理评估和强化微调的验证器
机构 * Chengdu Institute of Computer Applications, Chinese Academy of Sciences(中国科学院成都计算机应用研究所) ; School of Computer Science and Technology, University of Chinese Academy of Sciences(中国科学院大学计算机科学与技术学院)
专题命中 逻辑推理 :reasoning(title,abstract);logical reasoning(title,abstract);verifier(title,abstract);分类 cs.AI、cs.LG
AI总结 研究旨在为大语言模型逻辑推理评估及强化微调提供工具。核心方法是SATQuest,它能从CNF实例生成推理任务并客观检查答案,从多维度评估。主要贡献是通过该工具发现模型逻辑推理差距,证明强化微调有效果但跨格式鲁棒性待提升,还提供了相关研究基础设施。
Comments 23 pages, 8 figures. ACL 2026 Main Conference long paper (oral presentation)
Journal ref Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 2109-2131. Association for Computational Linguistics, 2026