TAGS：一种测试时通用-专用框架，结合检索增强推理与验证

TAGS: A Test-Time Generalist-Specialist Framework with Retrieval-Augmented Reasoning and Verification

May 23, 2025

作者: Jianghao Wu, Feilong Tang, Yulong Li, Ming Hu, Haochen Xue, Shoaib Jameel, Yutong Xie, Imran Razzak

cs.AI

摘要

近期，如思维链提示（Chain-of-Thought prompting）等进展显著提升了大型语言模型（LLMs）在零样本医疗推理中的表现。然而，基于提示的方法往往显得浅显且不稳定，而经过微调的医疗LLMs则在分布变化下泛化能力差，对未见过的临床场景适应有限。为应对这些局限，我们提出了TAGS，一个测试时框架，它结合了广泛能力的通才与领域专才，无需模型微调或参数更新，即可提供互补视角。为支持这一通才-专才推理过程，我们引入了两个辅助模块：一个分层检索机制，通过基于语义和推理层面相似性选择示例，提供多尺度范例；以及一个可靠性评分器，评估推理一致性以指导最终答案的聚合。TAGS在九项MedQA基准测试中均表现出色，将GPT-4o的准确率提升了13.8%，DeepSeek-R1提升了16.8%，并将一个基础7B模型的准确率从14.1%提升至23.9%。这些成果超越了多个经过微调的医疗LLMs，且无需任何参数更新。代码将在https://github.com/JianghaoWu/TAGS 提供。

English

Recent advances such as Chain-of-Thought prompting have significantly improved large language models (LLMs) in zero-shot medical reasoning. However, prompting-based methods often remain shallow and unstable, while fine-tuned medical LLMs suffer from poor generalization under distribution shifts and limited adaptability to unseen clinical scenarios. To address these limitations, we present TAGS, a test-time framework that combines a broadly capable generalist with a domain-specific specialist to offer complementary perspectives without any model fine-tuning or parameter updates. To support this generalist-specialist reasoning process, we introduce two auxiliary modules: a hierarchical retrieval mechanism that provides multi-scale exemplars by selecting examples based on both semantic and rationale-level similarity, and a reliability scorer that evaluates reasoning consistency to guide final answer aggregation. TAGS achieves strong performance across nine MedQA benchmarks, boosting GPT-4o accuracy by 13.8%, DeepSeek-R1 by 16.8%, and improving a vanilla 7B model from 14.1% to 23.9%. These results surpass several fine-tuned medical LLMs, without any parameter updates. The code will be available at https://github.com/JianghaoWu/TAGS.