@inproceedings{li-etal-2026-medcoach,
title = "{M}ed{C}oach: Enhancing Medical Reasoning in {LLM}s via Knowledge Graph-Augmented Chain-of-Thought Distillation",
author = "Li, Chuan and
Lyu, Ye and
Wang, Chengyu and
Fan, Mingyuan and
Chen, Cen",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-acl.1683/",
pages = "33724--33743",
ISBN = "979-8-89176-395-1",
abstract = "Despite the advanced capabilities of Large Language Models (LLMs), training specialized reasoning models for the medical domain remains a significant challenge due to the scarcity of high-quality, large-scale Chain-of-Thought (CoT) data. Moreover, the intermediate reasoning steps in teacher-generated CoT data can be redundant and noisy, leading models to acquire spurious patterns and resulting in suboptimal performance. To address these issues, we propose MedCoach, a novel framework that introduces a dedicated coach role to guide the student model through question decomposition, thereby smoothing its learning curve in medical reasoning. The framework employs a curriculum-oriented warm-up on simplified sub-questions, facilitating domain adaptation before advancing to complex long-chain reasoning. To ensure the fidelity of the intermediate chain-of-thought signals, we augment this phase with medical knowledge graphs to suppress factual drift and mitigate reasoning noise at a granular level.Subsequently, we introduce a targeted factual perturbation mechanism to foster fine-grained discrimination between valid fact utilization and subtle factual misapplications. Extensive experiments across diverse benchmarks demonstrate notable improvements over existing methods, validating the effectiveness of MedCoach."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2026-medcoach">
<titleInfo>
<title>MedCoach: Enhancing Medical Reasoning in LLMs via Knowledge Graph-Augmented Chain-of-Thought Distillation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chuan</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ye</namePart>
<namePart type="family">Lyu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengyu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mingyuan</namePart>
<namePart type="family">Fan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cen</namePart>
<namePart type="family">Chen</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>Findings of the Association for Computational Linguistics: ACL 2026</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">979-8-89176-395-1</identifier>
</relatedItem>
<abstract>Despite the advanced capabilities of Large Language Models (LLMs), training specialized reasoning models for the medical domain remains a significant challenge due to the scarcity of high-quality, large-scale Chain-of-Thought (CoT) data. Moreover, the intermediate reasoning steps in teacher-generated CoT data can be redundant and noisy, leading models to acquire spurious patterns and resulting in suboptimal performance. To address these issues, we propose MedCoach, a novel framework that introduces a dedicated coach role to guide the student model through question decomposition, thereby smoothing its learning curve in medical reasoning. The framework employs a curriculum-oriented warm-up on simplified sub-questions, facilitating domain adaptation before advancing to complex long-chain reasoning. To ensure the fidelity of the intermediate chain-of-thought signals, we augment this phase with medical knowledge graphs to suppress factual drift and mitigate reasoning noise at a granular level.Subsequently, we introduce a targeted factual perturbation mechanism to foster fine-grained discrimination between valid fact utilization and subtle factual misapplications. Extensive experiments across diverse benchmarks demonstrate notable improvements over existing methods, validating the effectiveness of MedCoach.</abstract>
<identifier type="citekey">li-etal-2026-medcoach</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.1683/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>33724</start>
<end>33743</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MedCoach: Enhancing Medical Reasoning in LLMs via Knowledge Graph-Augmented Chain-of-Thought Distillation
%A Li, Chuan
%A Lyu, Ye
%A Wang, Chengyu
%A Fan, Mingyuan
%A Chen, Cen
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F li-etal-2026-medcoach
%X Despite the advanced capabilities of Large Language Models (LLMs), training specialized reasoning models for the medical domain remains a significant challenge due to the scarcity of high-quality, large-scale Chain-of-Thought (CoT) data. Moreover, the intermediate reasoning steps in teacher-generated CoT data can be redundant and noisy, leading models to acquire spurious patterns and resulting in suboptimal performance. To address these issues, we propose MedCoach, a novel framework that introduces a dedicated coach role to guide the student model through question decomposition, thereby smoothing its learning curve in medical reasoning. The framework employs a curriculum-oriented warm-up on simplified sub-questions, facilitating domain adaptation before advancing to complex long-chain reasoning. To ensure the fidelity of the intermediate chain-of-thought signals, we augment this phase with medical knowledge graphs to suppress factual drift and mitigate reasoning noise at a granular level.Subsequently, we introduce a targeted factual perturbation mechanism to foster fine-grained discrimination between valid fact utilization and subtle factual misapplications. Extensive experiments across diverse benchmarks demonstrate notable improvements over existing methods, validating the effectiveness of MedCoach.
%U https://aclanthology.org/2026.findings-acl.1683/
%P 33724-33743
Markdown (Informal)
[MedCoach: Enhancing Medical Reasoning in LLMs via Knowledge Graph-Augmented Chain-of-Thought Distillation](https://aclanthology.org/2026.findings-acl.1683/) (Li et al., Findings 2026)
ACL