@inproceedings{han-etal-2026-tcmphal,
title = "{TCMPH}al: A Large-scale Dataset for Hallucination Detection in Traditional {C}hinese Medicine Pharmacy",
author = "Han, Nijia and
Wang, Zimu and
Xie, Ziwen and
Wang, Wei and
Meng, Jia and
Moraros, John and
Wang, Shuihua",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.552/",
doi = "10.63317/2889b9sdvrsm",
pages = "6939--6948",
abstract = "The rapid proliferation of large language models (LLMs) in medicine highlights their potential to revolutionize research in Traditional Chinese Medicine (TCM). While these models have shown great promise in assisting TCM practitioners by answering herb-related questions, generating syndrome-differentiation reports, and recommending classical formulas, a persistent challenge that arises is the issue of hallucination, where LLMs might produce content that appears plausible yet inaccurate. This issue has received limited attention within the context of TCM research, leaving a significant gap in understanding how hallucination manifests within the unique theoretical frameworks and diagnostic principles. Motivated by this phenomenon, we present TCMPHal, the first dataset specifically curated for hallucination detection in TCM pharmacy, comprising 10,000 high-quality question-answer pairs with hallucination annotations. Our experimental results across diverse LLMs, under standard, knowledge-based, and search engine-augmented conditions, demonstrate the capabilities and limitations of these models. A notable observation is that, for thinking LLMs, incorporating search engine results yields minimal improvement over their intrinsic reasoning abilities. We further conduct an in-depth error analysis, paving the way for future research directions in this domain. We release the TCMPHal dataset at \url{https://github.com/hanninaa/TCMP}."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="han-etal-2026-tcmphal">
<titleInfo>
<title>TCMPHal: A Large-scale Dataset for Hallucination Detection in Traditional Chinese Medicine Pharmacy</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nijia</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zimu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ziwen</namePart>
<namePart type="family">Xie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jia</namePart>
<namePart type="family">Meng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="family">Moraros</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuihua</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The rapid proliferation of large language models (LLMs) in medicine highlights their potential to revolutionize research in Traditional Chinese Medicine (TCM). While these models have shown great promise in assisting TCM practitioners by answering herb-related questions, generating syndrome-differentiation reports, and recommending classical formulas, a persistent challenge that arises is the issue of hallucination, where LLMs might produce content that appears plausible yet inaccurate. This issue has received limited attention within the context of TCM research, leaving a significant gap in understanding how hallucination manifests within the unique theoretical frameworks and diagnostic principles. Motivated by this phenomenon, we present TCMPHal, the first dataset specifically curated for hallucination detection in TCM pharmacy, comprising 10,000 high-quality question-answer pairs with hallucination annotations. Our experimental results across diverse LLMs, under standard, knowledge-based, and search engine-augmented conditions, demonstrate the capabilities and limitations of these models. A notable observation is that, for thinking LLMs, incorporating search engine results yields minimal improvement over their intrinsic reasoning abilities. We further conduct an in-depth error analysis, paving the way for future research directions in this domain. We release the TCMPHal dataset at https://github.com/hanninaa/TCMP.</abstract>
<identifier type="citekey">han-etal-2026-tcmphal</identifier>
<identifier type="doi">10.63317/2889b9sdvrsm</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.552/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>6939</start>
<end>6948</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TCMPHal: A Large-scale Dataset for Hallucination Detection in Traditional Chinese Medicine Pharmacy
%A Han, Nijia
%A Wang, Zimu
%A Xie, Ziwen
%A Wang, Wei
%A Meng, Jia
%A Moraros, John
%A Wang, Shuihua
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F han-etal-2026-tcmphal
%X The rapid proliferation of large language models (LLMs) in medicine highlights their potential to revolutionize research in Traditional Chinese Medicine (TCM). While these models have shown great promise in assisting TCM practitioners by answering herb-related questions, generating syndrome-differentiation reports, and recommending classical formulas, a persistent challenge that arises is the issue of hallucination, where LLMs might produce content that appears plausible yet inaccurate. This issue has received limited attention within the context of TCM research, leaving a significant gap in understanding how hallucination manifests within the unique theoretical frameworks and diagnostic principles. Motivated by this phenomenon, we present TCMPHal, the first dataset specifically curated for hallucination detection in TCM pharmacy, comprising 10,000 high-quality question-answer pairs with hallucination annotations. Our experimental results across diverse LLMs, under standard, knowledge-based, and search engine-augmented conditions, demonstrate the capabilities and limitations of these models. A notable observation is that, for thinking LLMs, incorporating search engine results yields minimal improvement over their intrinsic reasoning abilities. We further conduct an in-depth error analysis, paving the way for future research directions in this domain. We release the TCMPHal dataset at https://github.com/hanninaa/TCMP.
%R 10.63317/2889b9sdvrsm
%U https://aclanthology.org/2026.lrec-1.552/
%U https://doi.org/10.63317/2889b9sdvrsm
%P 6939-6948
Markdown (Informal)
[TCMPHal: A Large-scale Dataset for Hallucination Detection in Traditional Chinese Medicine Pharmacy](https://aclanthology.org/2026.lrec-1.552/) (Han et al., LREC 2026)
ACL