@inproceedings{xu-etal-2026-pcoad,
title = "{PC}o{AD}: The Pharmaceutical Certificate of Analysis Dataset Based on {LLM}s Validation and Calibration",
author = "Xu, Yiming and
Huang, Zhaokang and
Yu, Haoran and
Wang, Fu Lee and
Hao, Tianyong",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.615/",
pages = "12928--12958",
ISBN = "979-8-89176-462-0",
abstract = "Artificial intelligence is now widely applied in drug discovery and development, accelerating the entry of novel pharmaceuticals into clinical practice. As the variety of drugs expands, the workload for pharmaceutical inspection has increased significantly, making the demand for automated verification of pharmaceutical inspection results increasingly urgent. However, current research lacks reliable evaluation methods and datasets. To address this issue, we construct a Pharmaceutical Certificate of Analysis Dataset (PCoAD) based on large language model validation and correction. This dataset comprises 4,272 manually verified pharmaceutical certificates of analysis (PCoAs) based on Chinese and U.S. pharmacopoeias, comprehensively testing the ability of model to verify pharmaceutical inspection processes. Based on PCoAD, we propose the Multi-Agent Cooperation based on Adaptive Retrieval (MACAR) framework. This framework employs text chunking, adaptive retrieval, and inference to validate PCoAs. Experimental results demonstrate that MACAR outperforms multiple state-of-the-art methods across various types of tasks."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-etal-2026-pcoad">
<titleInfo>
<title>PCoAD: The Pharmaceutical Certificate of Analysis Dataset Based on LLMs Validation and Calibration</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yiming</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhaokang</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haoran</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fu</namePart>
<namePart type="given">Lee</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tianyong</namePart>
<namePart type="family">Hao</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>Findings of the Association for Computational Linguistics: EMNLP 2026</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">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Artificial intelligence is now widely applied in drug discovery and development, accelerating the entry of novel pharmaceuticals into clinical practice. As the variety of drugs expands, the workload for pharmaceutical inspection has increased significantly, making the demand for automated verification of pharmaceutical inspection results increasingly urgent. However, current research lacks reliable evaluation methods and datasets. To address this issue, we construct a Pharmaceutical Certificate of Analysis Dataset (PCoAD) based on large language model validation and correction. This dataset comprises 4,272 manually verified pharmaceutical certificates of analysis (PCoAs) based on Chinese and U.S. pharmacopoeias, comprehensively testing the ability of model to verify pharmaceutical inspection processes. Based on PCoAD, we propose the Multi-Agent Cooperation based on Adaptive Retrieval (MACAR) framework. This framework employs text chunking, adaptive retrieval, and inference to validate PCoAs. Experimental results demonstrate that MACAR outperforms multiple state-of-the-art methods across various types of tasks.</abstract>
<identifier type="citekey">xu-etal-2026-pcoad</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.615/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>12928</start>
<end>12958</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PCoAD: The Pharmaceutical Certificate of Analysis Dataset Based on LLMs Validation and Calibration
%A Xu, Yiming
%A Huang, Zhaokang
%A Yu, Haoran
%A Wang, Fu Lee
%A Hao, Tianyong
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F xu-etal-2026-pcoad
%X Artificial intelligence is now widely applied in drug discovery and development, accelerating the entry of novel pharmaceuticals into clinical practice. As the variety of drugs expands, the workload for pharmaceutical inspection has increased significantly, making the demand for automated verification of pharmaceutical inspection results increasingly urgent. However, current research lacks reliable evaluation methods and datasets. To address this issue, we construct a Pharmaceutical Certificate of Analysis Dataset (PCoAD) based on large language model validation and correction. This dataset comprises 4,272 manually verified pharmaceutical certificates of analysis (PCoAs) based on Chinese and U.S. pharmacopoeias, comprehensively testing the ability of model to verify pharmaceutical inspection processes. Based on PCoAD, we propose the Multi-Agent Cooperation based on Adaptive Retrieval (MACAR) framework. This framework employs text chunking, adaptive retrieval, and inference to validate PCoAs. Experimental results demonstrate that MACAR outperforms multiple state-of-the-art methods across various types of tasks.
%U https://aclanthology.org/2026.findings-emnlp.615/
%P 12928-12958
Markdown (Informal)
[PCoAD: The Pharmaceutical Certificate of Analysis Dataset Based on LLMs Validation and Calibration](https://aclanthology.org/2026.findings-emnlp.615/) (Xu et al., Findings 2026)
ACL