To Reason or Not to: Selective Chain-of-Thought in Medical Question Answering
Department of Electrical and Computer Engineering(电气与计算机工程系);University of Minnesota(明尼苏达大学);Division of Computational Health Sciences, Department of Surgery(计算健康科学 division,外科系);Department of Computer Science and Engineering(计算机科学与工程系);Health Data Science, School of Public Health(公共卫生学院健康数据科学系)
Zaifu Zhan, Min Zeng, Shuang Zhou, Yiran Song, Xiaoyi Chen, Yu Hou, Yifan Wu, Yang Ruan, Rui Zhang
Objective: To improve the efficiency of medical question answering (MedQA) with large language models (LLMs) by avoiding unnecessary reasoning while maintaining accuracy.
Methods: We propose Selective Chain-of-Thought (Selective CoT), an inference-time strategy that first predicts whether a question requires reasoning and generates a rationale only when needed. Two open-source LLMs (Llama-3.1-8B and Qwen-2.5-7B) were evaluated on four biomedical QA benchmarks-HeadQA, MedQA-USMLE, MedMCQA, and PubMedQA. Metrics included accuracy, total generated tokens, and inference time.
Results: Selective CoT reduced inference time by 13-45% and token usage by 8-47% with minimal accuracy loss ($\leq$4\%). In some model-task pairs, it achieved both higher accuracy and greater efficiency than standard CoT. Compared with fixed-length CoT, Selective CoT reached similar or superior accuracy at substantially lower computational cost.
Discussion: Selective CoT dynamically balances reasoning depth and efficiency by invoking explicit reasoning only when beneficial, reducing redundancy on recall-type questions while preserving interpretability.
Conclusion: Selective CoT provides a simple, model-agnostic, and cost-effective approach for medical QA, aligning reasoning effort with question complexity to enhance real-world deployability of LLM-based clinical systems.
keqing: knowledge-based question answering is a nature chain-of-thought mentor of LLM
National Key Laboratory of Radar Signal Processing(雷达信号处理国家重点实验室);Xidian University(西安电子科技大学);School of Computer Science and Engineering(计算机科学与工程学院);Nanyang Technological University(南洋理工大学)
Mitigating Misleading Chain-of-Thought Reasoning with Selective Filtering
College of Zhiyuan, Shanghai Jiao Tong University(上海交通大学致远学院);School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University(上海交通大学电子信息与电气工程学院);Shanghai Jiao Tong University(上海交通大学)
Southeast University(东南大学);Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University) Ministry of Education(新一代人工智能技术及其交叉应用国家重点实验室);China Mobile Research Institute(中国移动研究院);Monash University(墨尔本大学);University of Manchester(曼彻斯特大学);University of Edinburgh(爱丁堡大学)
Fusing Bidirectional Chains of Thought and Reward Mechanisms A Method for Enhancing Question-Answering Capabilities of Large Language Models for Chinese Intangible Cultural Heritage
When to Read Documents or QA History: On Unified and Selective Open-domain QA
LG AI Research(LG人工智能研究院);SNU-LG AI Research Center(首尔国立大学-LG人工智能研究中心);Seoul National University(首尔国立大学);University of Illinois at Chicago(伊利诺伊大学芝加哥分校)
ThoughtSource: A central hub for large language model reasoning data
Medical University of Vienna(维也纳医科大学);Technical University of Denmark(丹麦技术大学);Copenhagen University Hospital(哥本哈根大学医院);The Royal Institute of Technology (KTH)(皇家理工学院(KTH))
Better Eyes, Better Thoughts: Why Vision Chain-of-Thought Fails in Medicine
Department of Computer Science, City University of Hong Kong (Dongguan)(香港城市大学(东莞)计算机科学系);College of Computing and Data Science (CCDS), Nanyang Technological University(南洋理工大学计算与数据科学学院);School of Computer Science, Northwestern Polytechnical University(西北工业大学计算机科学学院)
Separate First, Fuse Later: Mitigating Cross-Modal Interference in Audio-Visual LLMs Reasoning with Modality-Specific Chain-of-Thought
Tianjin Key Laboratory of Cognitive Computing(天津认知计算实验室);Tianjin University(天津大学);Huiyan Technology Company, Ltd.(慧颜科技有限公司);Chinese Academy of Sciences(中国科学院);Tencent(腾讯)
HypothesisMed: Inference-Time Answer Fusion and Structured Hypothesis-Space Reporting for Biomedical Question Answering
Department of Computer Science Rensselaer Polytechnic Institute(计算机科学系雷士打理工学院);Department of Biomedical Engineering Rensselaer Polytechnic Institute(生物医学工程系雷士打理工学院)
Soft-Prompting with Graph-of-Thought for Multi-modal Representation Learning
School of Computer Science, Wuhan University(武汉大学计算机学院);National Engineering Research Center for Multimedia Software(国家多媒体软件工程技术研究中心);School of Electronic Information Engineering, Henan Polytechnic Institute(河南工业职业技术学院电子信息工程学院);JD Explore Academy(京东探索研究院)