arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.20130cs.CLcs.AI
收藏

推理还是不推理:医学问答中的选择性推理

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

AI总结:

选择性推理通过动态调整推理深度和效率,提升医学问答的效率和准确性。

摘要:

目标:通过避免不必要的推理来提高大型语言模型(LLMs)在医学问答(MedQA)中的效率,同时保持准确性。 方法:我们提出了选择性推理(Selective CoT),一种推理时间策略,首先预测问题是否需要推理,并在需要时生成推理过程。两个开源LLM(Llama-3.1-8B和Qwen-2.5-7B)在四个生物医学QA基准测试中进行了评估——HeadQA、MedQA-USMLE、MedMCQA和PubMedQA。指标包括准确性、生成的总token数和推理时间。 结果:选择性CoT将推理时间减少了13-45%,token使用减少了8-47%,准确性损失最小(≤4%)。在某些模型-任务对中,它实现了更高的准确性和更大的效率,比标准CoT。与固定长度CoT相比,选择性CoT在显著更低的计算成本下达到了相似或更优的准确性。 讨论:选择性CoT通过仅在有益时调用显式推理来动态平衡推理深度和效率,减少对回忆型问题的冗余,同时保持可解释性。 结论:选择性CoT提供了一种简单、模型无关且成本效益高的方法来解决医学问答问题,使推理努力与问题复杂性相匹配,以增强基于LLM的临床系统的实际应用性。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑