@inproceedings{dou-etal-2024-detection-diagnosis,
title = "Detection, Diagnosis, and Explanation: A Benchmark for {C}hinese Medial Hallucination Evaluation",
author = "Dou, Chengfeng and
Zhang, Ying and
Chen, Yanyuan and
Jin, Zhi and
Jiao, Wenpin and
Zhao, Haiyan and
Huang, Yu",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.428",
pages = "4784--4794",
abstract = "Large Language Models (LLMs) have made significant progress recently. However, their practical use in healthcare is hindered by their tendency to generate hallucinations. One specific type, called snowballing hallucination, occurs when LLMs encounter misleading information, and poses a security threat to LLMs. To understand how well LLMs can resist these hallucination, we create the Chinese Medical Hallucination Evaluation benchmark (CMHE). This benchmark can be used to evaluate LLMs{'} ability to detect medical hallucinations, make accurate diagnoses in noisy conditions, and provide plausible explanations. The creation of this benchmark involves a combination of manual and model-based approaches. In addition, we use ICD-10 as well as MeSH, two specialized glossaries, to aid in the evaluation. Our experiments show that the LLM struggles to identify fake medical terms and makes poor diagnoses in distracting environments. However, improving the model{'}s understanding of medical concepts can help it resist interference to some extent.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dou-etal-2024-detection-diagnosis">
<titleInfo>
<title>Detection, Diagnosis, and Explanation: A Benchmark for Chinese Medial Hallucination Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chengfeng</namePart>
<namePart type="family">Dou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ying</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yanyuan</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhi</namePart>
<namePart type="family">Jin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenpin</namePart>
<namePart type="family">Jiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haiyan</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large Language Models (LLMs) have made significant progress recently. However, their practical use in healthcare is hindered by their tendency to generate hallucinations. One specific type, called snowballing hallucination, occurs when LLMs encounter misleading information, and poses a security threat to LLMs. To understand how well LLMs can resist these hallucination, we create the Chinese Medical Hallucination Evaluation benchmark (CMHE). This benchmark can be used to evaluate LLMs’ ability to detect medical hallucinations, make accurate diagnoses in noisy conditions, and provide plausible explanations. The creation of this benchmark involves a combination of manual and model-based approaches. In addition, we use ICD-10 as well as MeSH, two specialized glossaries, to aid in the evaluation. Our experiments show that the LLM struggles to identify fake medical terms and makes poor diagnoses in distracting environments. However, improving the model’s understanding of medical concepts can help it resist interference to some extent.</abstract>
<identifier type="citekey">dou-etal-2024-detection-diagnosis</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.428</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>4784</start>
<end>4794</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Detection, Diagnosis, and Explanation: A Benchmark for Chinese Medial Hallucination Evaluation
%A Dou, Chengfeng
%A Zhang, Ying
%A Chen, Yanyuan
%A Jin, Zhi
%A Jiao, Wenpin
%A Zhao, Haiyan
%A Huang, Yu
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F dou-etal-2024-detection-diagnosis
%X Large Language Models (LLMs) have made significant progress recently. However, their practical use in healthcare is hindered by their tendency to generate hallucinations. One specific type, called snowballing hallucination, occurs when LLMs encounter misleading information, and poses a security threat to LLMs. To understand how well LLMs can resist these hallucination, we create the Chinese Medical Hallucination Evaluation benchmark (CMHE). This benchmark can be used to evaluate LLMs’ ability to detect medical hallucinations, make accurate diagnoses in noisy conditions, and provide plausible explanations. The creation of this benchmark involves a combination of manual and model-based approaches. In addition, we use ICD-10 as well as MeSH, two specialized glossaries, to aid in the evaluation. Our experiments show that the LLM struggles to identify fake medical terms and makes poor diagnoses in distracting environments. However, improving the model’s understanding of medical concepts can help it resist interference to some extent.
%U https://aclanthology.org/2024.lrec-main.428
%P 4784-4794
Markdown (Informal)
[Detection, Diagnosis, and Explanation: A Benchmark for Chinese Medial Hallucination Evaluation](https://aclanthology.org/2024.lrec-main.428) (Dou et al., LREC-COLING 2024)
ACL
- Chengfeng Dou, Ying Zhang, Yanyuan Chen, Zhi Jin, Wenpin Jiao, Haiyan Zhao, and Yu Huang. 2024. Detection, Diagnosis, and Explanation: A Benchmark for Chinese Medial Hallucination Evaluation. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 4784–4794, Torino, Italia. ELRA and ICCL.