@inproceedings{qiu-etal-2025-training,
title = "Training Medical {QA} Models Based on Mixed Rewards from Multiple-Choice and Open-Ended Questions",
author = "Qiu, Yue and
Ting, Yujan and
Dong, Pei and
Chen, Terrence and
Huang, Weijing",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-emnlp.463/",
pages = "8721--8729",
ISBN = "979-8-89176-335-7",
abstract = "Reinforcement learning (RL) for large language models (LLMs) typically requires clear reward signals, which are often unavailable for open-ended (OE) questions where answer evaluation is ambiguous without scalable expert labeling. We investigate whether LLMs benefit from training on mixed data with varying reward clarity. Our approach combines Multiple-choice questions (MCQs), which offer clear binary rewards, with OE questions, for which we use simpler, potentially noisy rewards such as Jaccard similarity or LLM-based evaluators. We hypothesize that MCQs can stabilize training when mixed with OE questions. Our experiments show this mixed-data approach consistently improves medical question-answering performance across model scales."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="qiu-etal-2025-training">
<titleInfo>
<title>Training Medical QA Models Based on Mixed Rewards from Multiple-Choice and Open-Ended Questions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Qiu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yujan</namePart>
<namePart type="family">Ting</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pei</namePart>
<namePart type="family">Dong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Terrence</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weijing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-335-7</identifier>
</relatedItem>
<abstract>Reinforcement learning (RL) for large language models (LLMs) typically requires clear reward signals, which are often unavailable for open-ended (OE) questions where answer evaluation is ambiguous without scalable expert labeling. We investigate whether LLMs benefit from training on mixed data with varying reward clarity. Our approach combines Multiple-choice questions (MCQs), which offer clear binary rewards, with OE questions, for which we use simpler, potentially noisy rewards such as Jaccard similarity or LLM-based evaluators. We hypothesize that MCQs can stabilize training when mixed with OE questions. Our experiments show this mixed-data approach consistently improves medical question-answering performance across model scales.</abstract>
<identifier type="citekey">qiu-etal-2025-training</identifier>
<location>
<url>https://aclanthology.org/2025.findings-emnlp.463/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>8721</start>
<end>8729</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Training Medical QA Models Based on Mixed Rewards from Multiple-Choice and Open-Ended Questions
%A Qiu, Yue
%A Ting, Yujan
%A Dong, Pei
%A Chen, Terrence
%A Huang, Weijing
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Findings of the Association for Computational Linguistics: EMNLP 2025
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-335-7
%F qiu-etal-2025-training
%X Reinforcement learning (RL) for large language models (LLMs) typically requires clear reward signals, which are often unavailable for open-ended (OE) questions where answer evaluation is ambiguous without scalable expert labeling. We investigate whether LLMs benefit from training on mixed data with varying reward clarity. Our approach combines Multiple-choice questions (MCQs), which offer clear binary rewards, with OE questions, for which we use simpler, potentially noisy rewards such as Jaccard similarity or LLM-based evaluators. We hypothesize that MCQs can stabilize training when mixed with OE questions. Our experiments show this mixed-data approach consistently improves medical question-answering performance across model scales.
%U https://aclanthology.org/2025.findings-emnlp.463/
%P 8721-8729
Markdown (Informal)
[Training Medical QA Models Based on Mixed Rewards from Multiple-Choice and Open-Ended Questions](https://aclanthology.org/2025.findings-emnlp.463/) (Qiu et al., Findings 2025)
ACL