@inproceedings{wu-etal-2026-camec,
title = "{CAMEC}: Complexity-Aware Multi-Expert Collaboration for Reliable {C}hinese Medical Question Answering",
author = "Wu, Yukang and
Jia, Xiyuan and
Wu, Jiayi and
Yu, HongChen and
Qiu, Yuhan and
Guohua, Wu",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-long.1781/",
pages = "38427--38457",
ISBN = "979-8-89176-390-6",
abstract = "Large language models (LLMs) are promising for medical question answering (QA) but remain unreliable in Chinese clinical settings due to hallucinations, weak factual grounding, and difficulty handling clinically complex cases. We propose CAMEC (Complexity-Aware Multi-Expert Collaboration), a framework that combines hierarchical medical adaptation with complexity-aware expert routing for reliable Chinese medical QA. We adopt a three-stage LoRA-based supervised fine-tuning pipeline for domain adaptation, instruction following, and clinical reasoning. At inference, CAMEC routes each query by predicted complexity and selectively recruits three experts: an internal chain-of-thought (CoT) expert, a retrieval-augmented expert over a dense medical vector database, and a knowledge graph (KG) expert over a structured medical knowledge base. An LLM-as-a-Judge module evaluates and critiques expert reports, iteratively refining them into a consensus answer. Experiments on four Chinese medical benchmarks show that CAMEC consistentlyoutperforms strong general and medical LLM baselines, achieving 78.86{\%} (CMExam), 84.15{\%} (MedQA-CN), 78.51{\%} (CMMLU-Med), and 74.40{\%} (CMB-exam), with consistent absolute improvements over the previous state-of-the-artHuatuoGPT-o1-7B across all benchmarks. The complexity-aware router reduces expert invocations and inference cost, making CAMEC both highly effective and computationally efficient."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wu-etal-2026-camec">
<titleInfo>
<title>CAMEC: Complexity-Aware Multi-Expert Collaboration for Reliable Chinese Medical Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yukang</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiyuan</namePart>
<namePart type="family">Jia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiayi</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">HongChen</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuhan</namePart>
<namePart type="family">Qiu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wu</namePart>
<namePart type="family">Guohua</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-390-6</identifier>
</relatedItem>
<abstract>Large language models (LLMs) are promising for medical question answering (QA) but remain unreliable in Chinese clinical settings due to hallucinations, weak factual grounding, and difficulty handling clinically complex cases. We propose CAMEC (Complexity-Aware Multi-Expert Collaboration), a framework that combines hierarchical medical adaptation with complexity-aware expert routing for reliable Chinese medical QA. We adopt a three-stage LoRA-based supervised fine-tuning pipeline for domain adaptation, instruction following, and clinical reasoning. At inference, CAMEC routes each query by predicted complexity and selectively recruits three experts: an internal chain-of-thought (CoT) expert, a retrieval-augmented expert over a dense medical vector database, and a knowledge graph (KG) expert over a structured medical knowledge base. An LLM-as-a-Judge module evaluates and critiques expert reports, iteratively refining them into a consensus answer. Experiments on four Chinese medical benchmarks show that CAMEC consistentlyoutperforms strong general and medical LLM baselines, achieving 78.86% (CMExam), 84.15% (MedQA-CN), 78.51% (CMMLU-Med), and 74.40% (CMB-exam), with consistent absolute improvements over the previous state-of-the-artHuatuoGPT-o1-7B across all benchmarks. The complexity-aware router reduces expert invocations and inference cost, making CAMEC both highly effective and computationally efficient.</abstract>
<identifier type="citekey">wu-etal-2026-camec</identifier>
<location>
<url>https://aclanthology.org/2026.acl-long.1781/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>38427</start>
<end>38457</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CAMEC: Complexity-Aware Multi-Expert Collaboration for Reliable Chinese Medical Question Answering
%A Wu, Yukang
%A Jia, Xiyuan
%A Wu, Jiayi
%A Yu, HongChen
%A Qiu, Yuhan
%A Guohua, Wu
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-390-6
%F wu-etal-2026-camec
%X Large language models (LLMs) are promising for medical question answering (QA) but remain unreliable in Chinese clinical settings due to hallucinations, weak factual grounding, and difficulty handling clinically complex cases. We propose CAMEC (Complexity-Aware Multi-Expert Collaboration), a framework that combines hierarchical medical adaptation with complexity-aware expert routing for reliable Chinese medical QA. We adopt a three-stage LoRA-based supervised fine-tuning pipeline for domain adaptation, instruction following, and clinical reasoning. At inference, CAMEC routes each query by predicted complexity and selectively recruits three experts: an internal chain-of-thought (CoT) expert, a retrieval-augmented expert over a dense medical vector database, and a knowledge graph (KG) expert over a structured medical knowledge base. An LLM-as-a-Judge module evaluates and critiques expert reports, iteratively refining them into a consensus answer. Experiments on four Chinese medical benchmarks show that CAMEC consistentlyoutperforms strong general and medical LLM baselines, achieving 78.86% (CMExam), 84.15% (MedQA-CN), 78.51% (CMMLU-Med), and 74.40% (CMB-exam), with consistent absolute improvements over the previous state-of-the-artHuatuoGPT-o1-7B across all benchmarks. The complexity-aware router reduces expert invocations and inference cost, making CAMEC both highly effective and computationally efficient.
%U https://aclanthology.org/2026.acl-long.1781/
%P 38427-38457
Markdown (Informal)
[CAMEC: Complexity-Aware Multi-Expert Collaboration for Reliable Chinese Medical Question Answering](https://aclanthology.org/2026.acl-long.1781/) (Wu et al., ACL 2026)
ACL