<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="iwase-etal-2026-medrect">
    <titleInfo>
        <title>MedRECT: A Bilingual Medical Reasoning Benchmark for Error Correction in Clinical Texts</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Naoto</namePart>
        <namePart type="family">Iwase</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hiroki</namePart>
        <namePart type="family">Okuyama</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Junichiro</namePart>
        <namePart type="family">Iwasawa</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>The Proceedings of the Workshop on Open Reasoning Across Cultures Languages (ORACLE)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Leonardo</namePart>
            <namePart type="family">Ranaldi</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Giulia</namePart>
            <namePart type="family">Pucci</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Federico</namePart>
            <namePart type="family">Ranaldi</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Marco</namePart>
            <namePart type="family">Valentino</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Alexandra</namePart>
            <namePart type="family">Birch</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Fabio</namePart>
            <namePart type="given">Massimo</namePart>
            <namePart type="family">Zanzotto</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">979-8-89176-483-5</identifier>
    </relatedItem>
    <abstract>Large language models (LLMs) show promise in medical applications, but their ability to detect and correct errors in clinical texts remains under-evaluated, particularly beyond English. We introduce M ED RECT, a bilingual benchmark for Japanese and English that formulates medical error handling as three subtasks: error detection, error sentence extraction, and error correction. M ED RECT-ja contains 663 samples derived from the Japanese Medical Licensing Examinations, while the separately sourced M ED RECT-en contains 458 samples curated from MEDEC. We evaluate 11 LLMs across 17 configurations that cover proprietary and openweight models, medical-domain specialization, and multiple reasoning settings. Qwen3-32B scores higher in its thinking mode than in its non-thinking mode on error detection F1 and sentence extraction accuracy in both subsets, with sentence extraction accuracy higher by 24.5 percentage points on M ED RECT-ja and 10.3 on M ED RECT-en. Several leading general-purpose reasoning models outperform all three evaluated medical-domain models on these two subtasks. Most models have lower point estimates on the Japanese subset, although absolute scores are not directly comparable because the subsets differ in source material and error distributions. LoRA finetuning yields higher sentence extraction accuracy and higher point estimates on all three reference-based correction similarity metrics in both languages. M ED RECT provides an open, reusable evaluation resource for studying medical error correction and reasoning across Japanese and English.</abstract>
    <identifier type="citekey">iwase-etal-2026-medrect</identifier>
    <location>
        <url>https://aclanthology.org/2026.oracle-main.10/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>150</start>
            <end>165</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T MedRECT: A Bilingual Medical Reasoning Benchmark for Error Correction in Clinical Texts
%A Iwase, Naoto
%A Okuyama, Hiroki
%A Iwasawa, Junichiro
%Y Ranaldi, Leonardo
%Y Pucci, Giulia
%Y Ranaldi, Federico
%Y Valentino, Marco
%Y Birch, Alexandra
%Y Zanzotto, Fabio Massimo
%S The Proceedings of the Workshop on Open Reasoning Across Cultures Languages (ORACLE)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-483-5
%F iwase-etal-2026-medrect
%X Large language models (LLMs) show promise in medical applications, but their ability to detect and correct errors in clinical texts remains under-evaluated, particularly beyond English. We introduce M ED RECT, a bilingual benchmark for Japanese and English that formulates medical error handling as three subtasks: error detection, error sentence extraction, and error correction. M ED RECT-ja contains 663 samples derived from the Japanese Medical Licensing Examinations, while the separately sourced M ED RECT-en contains 458 samples curated from MEDEC. We evaluate 11 LLMs across 17 configurations that cover proprietary and openweight models, medical-domain specialization, and multiple reasoning settings. Qwen3-32B scores higher in its thinking mode than in its non-thinking mode on error detection F1 and sentence extraction accuracy in both subsets, with sentence extraction accuracy higher by 24.5 percentage points on M ED RECT-ja and 10.3 on M ED RECT-en. Several leading general-purpose reasoning models outperform all three evaluated medical-domain models on these two subtasks. Most models have lower point estimates on the Japanese subset, although absolute scores are not directly comparable because the subsets differ in source material and error distributions. LoRA finetuning yields higher sentence extraction accuracy and higher point estimates on all three reference-based correction similarity metrics in both languages. M ED RECT provides an open, reusable evaluation resource for studying medical error correction and reasoning across Japanese and English.
%U https://aclanthology.org/2026.oracle-main.10/
%P 150-165

Markdown (Informal)

[MedRECT: A Bilingual Medical Reasoning Benchmark for Error Correction in Clinical Texts](https://aclanthology.org/2026.oracle-main.10/) (Iwase et al., ORACLE 2026)

• MedRECT: A Bilingual Medical Reasoning Benchmark for Error Correction in Clinical Texts (Iwase et al., ORACLE 2026)

ACL

• Naoto Iwase, Hiroki Okuyama, and Junichiro Iwasawa. 2026. MedRECT: A Bilingual Medical Reasoning Benchmark for Error Correction in Clinical Texts. In The Proceedings of the Workshop on Open Reasoning Across Cultures Languages (ORACLE), pages 150–165, Budapest, Hungary. Association for Computational Linguistics.