@inproceedings{xiao-etal-2026-decisions,
title = "Decisions by Discrimination: Differential Evidence for Medical Reasoning",
author = "Xiao, Yunpeng and
Xie, Yuzhang and
Huang, Junhao and
Yang, Carl and
Hu, Xiao and
Shu, Kai",
editor = "Zhang, Yue and
Xu, Ruifeng and
Purwarianti, Ayu and
Rong, Tong and
Suzuki, Jun",
booktitle = "Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the {A}sia-Pacific Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.aacl-long.250/",
pages = "5589--5603",
ISBN = "979-8-89176-439-2",
abstract = "Large language models (LLMs) are increasingly studied for clinical decision support, and medical question answering provides an effective testbed for evaluating this capability. In particular, medical multiple-choice questions (MCQs) reflect a core challenge in clinical decision-making: plausible options often share substantial overlapping evidence, while only a few decisive factors distinguish the correct option from other incorrect ones. However, existing retrieval-based and reasoning-oriented methods mainly focus on supplying broadly relevant knowledge or eliciting reasoning paths, rather than identifying the compact differential evidence that separates confusing alternatives. In this work, we present a retrieval-grounded differential evidence framework for medical MCQs. Our method extracts option-specific pieces of differential evidence and organizes them into concise evidence prompts for answer selection. This design better aligns external knowledge with differential reasoning while reducing irrelevant context. Experiments show consistent accuracy gains over strong baselines. Ablation studies further show that our framework outperforms both directly using retrieved evidence chunks and closed-source LLM-generated general hints, and that its improvements are not solely explained by answer-proximal guidance, but are consistent with differential evidence serving as a compact aid for reasoning over competing alternatives. Our findings also offer insights for medical reasoning and other decision-making settings with multiple possible choices."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xiao-etal-2026-decisions">
<titleInfo>
<title>Decisions by Discrimination: Differential Evidence for Medical Reasoning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yunpeng</namePart>
<namePart type="family">Xiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuzhang</namePart>
<namePart type="family">Xie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junhao</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carl</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiao</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kai</namePart>
<namePart type="family">Shu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruifeng</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayu</namePart>
<namePart type="family">Purwarianti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Rong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Suzuki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-439-2</identifier>
</relatedItem>
<abstract>Large language models (LLMs) are increasingly studied for clinical decision support, and medical question answering provides an effective testbed for evaluating this capability. In particular, medical multiple-choice questions (MCQs) reflect a core challenge in clinical decision-making: plausible options often share substantial overlapping evidence, while only a few decisive factors distinguish the correct option from other incorrect ones. However, existing retrieval-based and reasoning-oriented methods mainly focus on supplying broadly relevant knowledge or eliciting reasoning paths, rather than identifying the compact differential evidence that separates confusing alternatives. In this work, we present a retrieval-grounded differential evidence framework for medical MCQs. Our method extracts option-specific pieces of differential evidence and organizes them into concise evidence prompts for answer selection. This design better aligns external knowledge with differential reasoning while reducing irrelevant context. Experiments show consistent accuracy gains over strong baselines. Ablation studies further show that our framework outperforms both directly using retrieved evidence chunks and closed-source LLM-generated general hints, and that its improvements are not solely explained by answer-proximal guidance, but are consistent with differential evidence serving as a compact aid for reasoning over competing alternatives. Our findings also offer insights for medical reasoning and other decision-making settings with multiple possible choices.</abstract>
<identifier type="citekey">xiao-etal-2026-decisions</identifier>
<location>
<url>https://aclanthology.org/2026.aacl-long.250/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>5589</start>
<end>5603</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Decisions by Discrimination: Differential Evidence for Medical Reasoning
%A Xiao, Yunpeng
%A Xie, Yuzhang
%A Huang, Junhao
%A Yang, Carl
%A Hu, Xiao
%A Shu, Kai
%Y Zhang, Yue
%Y Xu, Ruifeng
%Y Purwarianti, Ayu
%Y Rong, Tong
%Y Suzuki, Jun
%S Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-439-2
%F xiao-etal-2026-decisions
%X Large language models (LLMs) are increasingly studied for clinical decision support, and medical question answering provides an effective testbed for evaluating this capability. In particular, medical multiple-choice questions (MCQs) reflect a core challenge in clinical decision-making: plausible options often share substantial overlapping evidence, while only a few decisive factors distinguish the correct option from other incorrect ones. However, existing retrieval-based and reasoning-oriented methods mainly focus on supplying broadly relevant knowledge or eliciting reasoning paths, rather than identifying the compact differential evidence that separates confusing alternatives. In this work, we present a retrieval-grounded differential evidence framework for medical MCQs. Our method extracts option-specific pieces of differential evidence and organizes them into concise evidence prompts for answer selection. This design better aligns external knowledge with differential reasoning while reducing irrelevant context. Experiments show consistent accuracy gains over strong baselines. Ablation studies further show that our framework outperforms both directly using retrieved evidence chunks and closed-source LLM-generated general hints, and that its improvements are not solely explained by answer-proximal guidance, but are consistent with differential evidence serving as a compact aid for reasoning over competing alternatives. Our findings also offer insights for medical reasoning and other decision-making settings with multiple possible choices.
%U https://aclanthology.org/2026.aacl-long.250/
%P 5589-5603
Markdown (Informal)
[Decisions by Discrimination: Differential Evidence for Medical Reasoning](https://aclanthology.org/2026.aacl-long.250/) (Xiao et al., AACL-IJCNLP 2026)
ACL
- Yunpeng Xiao, Yuzhang Xie, Junhao Huang, Carl Yang, Xiao Hu, and Kai Shu. 2026. Decisions by Discrimination: Differential Evidence for Medical Reasoning. In Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 5589–5603, Hengqin, China. Association for Computational Linguistics.