用多个开源大模型协作回答生物医学问题，效果优于单一模型。
Harnessing Collective Intelligence of LLMs for Robust Biomedical QA: A Multi-Model Approach
- 多模型协同：用13个开源大模型并行答题，按类型组合输出。
- 精准高效：在2025年生物医学问答挑战赛中多次夺冠，尤其在精确答案上表现突出。
- 实用指南：揭示不同问题类型适配的最佳模型组合，可直接复用。
生物医学文本挖掘与问答是重要但极具挑战的任务，尤其面对文献量的指数级增长。本文参与第13届BioASQ挑战赛，针对任务13b的生物医学语义问答及联合任务（Synergy）的开发主题问答。我们部署一系列开源大语言模型（LLMs）作为检索增强生成器来回答生物医学问题，不同模型处理同一问题，通过多数投票决定是非类问题的答案，对列表型和事实型问题则采用答案并集策略。我们评估了13个最先进的开源LLM，探索所有可能的模型组合以生成最终答案，为每种问题类型定制了最优的LLM流水线。研究发现，特定模型组合在特定问题类型上持续表现更优。在2025年挑战赛四轮中，我们的系统取得显著成绩：在联合任务中，第二轮获得理想答案第一名、精确答案第二名；第三、第四轮均以精确答案并列第一。
原文摘要 · Abstract (English)
Biomedical text mining and question-answering are essential yet highly demanding tasks, particularly in the face of the exponential growth of biomedical literature. In this work, we present our participation in the 13th edition of the BioASQ challenge, which involves biomedical semantic question-answering for Task 13b and biomedical question-answering for developing topics for the Synergy task. We deploy a selection of open-source large language models (LLMs) as retrieval-augmented generators to answer biomedical questions. Various models are used to process the questions. A majority voting system combines their output to determine the final answer for Yes/No questions, while for list and factoid type questions, the union of their answers in used. We evaluated 13 state-of-the-art open source LLMs, exploring all possible model combinations to contribute to the final answer, resulting in tailored LLM pipelines for each question type. Our findings provide valuable insight into which combinations of LLMs consistently produce superior results for specific question types. In the four rounds of the 2025 BioASQ challenge, our system achieved notable results: in the Synergy task, we secured 1st place for ideal answers and 2nd place for exact answers in round 2, as well as two shared 1st places for exact answers in round 3 and 4.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。