Paper
To Reason or Not to: Selective Chain-of-Thought in Medical Question Answering
Authors
Zaifu Zhan, Min Zeng, Shuang Zhou, Yiran Song, Xiaoyi Chen, Yu Hou, Yifan Wu, Yang Ruan, Rui Zhang
Abstract
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.
Metadata
Related papers
Vibe Coding XR: Accelerating AI + XR Prototyping with XR Blocks and Gemini
Ruofei Du, Benjamin Hersh, David Li, Nels Numan, Xun Qian, Yanhe Chen, Zhongy... • 2026-03-25
Comparing Developer and LLM Biases in Code Evaluation
Aditya Mittal, Ryan Shar, Zichu Wu, Shyam Agarwal, Tongshuang Wu, Chris Donah... • 2026-03-25
The Stochastic Gap: A Markovian Framework for Pre-Deployment Reliability and Oversight-Cost Auditing in Agentic Artificial Intelligence
Biplab Pal, Santanu Bhattacharya • 2026-03-25
Retrieval Improvements Do Not Guarantee Better Answers: A Study of RAG for AI Policy QA
Saahil Mathur, Ryan David Rittner, Vedant Ajit Thakur, Daniel Stuart Schiff, ... • 2026-03-25
MARCH: Multi-Agent Reinforced Self-Check for LLM Hallucination
Zhuo Li, Yupeng Zhang, Pengyu Cheng, Jiajun Song, Mengyu Zhou, Hao Li, Shujie... • 2026-03-25
Raw Data (Debug)
{
"raw_xml": "<entry>\n <id>http://arxiv.org/abs/2602.20130v1</id>\n <title>To Reason or Not to: Selective Chain-of-Thought in Medical Question Answering</title>\n <updated>2026-02-23T18:42:50Z</updated>\n <link href='https://arxiv.org/abs/2602.20130v1' rel='alternate' type='text/html'/>\n <link href='https://arxiv.org/pdf/2602.20130v1' rel='related' title='pdf' type='application/pdf'/>\n <summary>Objective: To improve the efficiency of medical question answering (MedQA) with large language models (LLMs) by avoiding unnecessary reasoning while maintaining accuracy.\n 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.\n 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.\n 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.\n 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.</summary>\n <category scheme='http://arxiv.org/schemas/atom' term='cs.CL'/>\n <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n <published>2026-02-23T18:42:50Z</published>\n <arxiv:primary_category term='cs.CL'/>\n <author>\n <name>Zaifu Zhan</name>\n </author>\n <author>\n <name>Min Zeng</name>\n </author>\n <author>\n <name>Shuang Zhou</name>\n </author>\n <author>\n <name>Yiran Song</name>\n </author>\n <author>\n <name>Xiaoyi Chen</name>\n </author>\n <author>\n <name>Yu Hou</name>\n </author>\n <author>\n <name>Yifan Wu</name>\n </author>\n <author>\n <name>Yang Ruan</name>\n </author>\n <author>\n <name>Rui Zhang</name>\n </author>\n </entry>"
}