<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2026-bridgegap">
    <titleInfo>
        <title>BridgeGap: Belief-Grounded Training for Medical Dialogue Agents</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Weijun</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Tao</namePart>
        <namePart type="family">Yang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jiayu</namePart>
        <namePart type="family">Yang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Fei</namePart>
        <namePart type="family">Chao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Hung-Yi</namePart>
            <namePart type="family">Lee</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sunipa</namePart>
            <namePart type="family">Dev</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jessy</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Desmond</namePart>
            <namePart type="family">Elliott</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Budapest, Hungary</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-459-0</identifier>
    </relatedItem>
    <abstract>Although LLMs perform well on static medical QA, adapting them to multi-turn diagnostic dialogue remains challenging: agents forget confirmed symptoms, ask redundant questions, and fail to narrow differentials, largely because they lack an explicit representation of their evolving clinical understanding. Our key insight is that a structured belief state—encoding accumulated evidence, ranked differential diagnoses with confidence, and prioritized next questions—can simultaneously serve as a supervision target, a basis for rule-based reward computation, and a grounding context for deciding what to ask next. We propose BridgeGap, a two-stage framework in which supervised fine-tuning on silver-annotated belief states teaches the agent to maintain structured clinical reasoning, while reinforcement learning with a belief-progress reward refines questioning strategy through dense, environment-verified per-turn feedback without LLM judges or learned reward models. On HealthBench, BridgeGap (8B) surpasses Doctor-R1 (8B) by 2.84 points and the 4× larger Baichuan-M2-32B by 5.85 points; on AgentClinic, it achieves 44.6% diagnostic accuracy in 10.5 average turns, compared to 37.6% in 15.5 turns for Doctor-R1. Across evaluations, BridgeGap advances interactive diagnosis while preserving factual knowledge on static medical benchmarks.</abstract>
    <identifier type="citekey">li-etal-2026-bridgegap</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.1974/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>44932</start>
            <end>44947</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T BridgeGap: Belief-Grounded Training for Medical Dialogue Agents
%A Li, Weijun
%A Yang, Tao
%A Yang, Jiayu
%A Chao, Fei
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F li-etal-2026-bridgegap
%X Although LLMs perform well on static medical QA, adapting them to multi-turn diagnostic dialogue remains challenging: agents forget confirmed symptoms, ask redundant questions, and fail to narrow differentials, largely because they lack an explicit representation of their evolving clinical understanding. Our key insight is that a structured belief state—encoding accumulated evidence, ranked differential diagnoses with confidence, and prioritized next questions—can simultaneously serve as a supervision target, a basis for rule-based reward computation, and a grounding context for deciding what to ask next. We propose BridgeGap, a two-stage framework in which supervised fine-tuning on silver-annotated belief states teaches the agent to maintain structured clinical reasoning, while reinforcement learning with a belief-progress reward refines questioning strategy through dense, environment-verified per-turn feedback without LLM judges or learned reward models. On HealthBench, BridgeGap (8B) surpasses Doctor-R1 (8B) by 2.84 points and the 4× larger Baichuan-M2-32B by 5.85 points; on AgentClinic, it achieves 44.6% diagnostic accuracy in 10.5 average turns, compared to 37.6% in 15.5 turns for Doctor-R1. Across evaluations, BridgeGap advances interactive diagnosis while preserving factual knowledge on static medical benchmarks.
%U https://aclanthology.org/2026.emnlp-main.1974/
%P 44932-44947

Markdown (Informal)

[BridgeGap: Belief-Grounded Training for Medical Dialogue Agents](https://aclanthology.org/2026.emnlp-main.1974/) (Li et al., EMNLP 2026)

• BridgeGap: Belief-Grounded Training for Medical Dialogue Agents (Li et al., EMNLP 2026)

ACL

• Weijun Li, Tao Yang, Jiayu Yang, and Fei Chao. 2026. BridgeGap: Belief-Grounded Training for Medical Dialogue Agents. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 44932–44947, Budapest, Hungary. Association for Computational Linguistics.