@inproceedings{guo-etal-2026-attention,
title = "Attention-Weighted Retrieval-Augmented Data Engineering for {ADR} Severity Classification",
author = "Guo, David and
Vishwamitra, Nishant and
Choo, Kim-Kwang Raymond",
editor = "Atanasova, Pepa and
Haffari, Gholamreza and
Wang, Minghan",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-industry.131/",
pages = "2234--2243",
ISBN = "979-8-89176-460-6",
abstract = "Adverse drug reaction (ADR) severity prediction is a key task in pharmacovigilance and post-market drug safety surveillance, but is of- ten challenged by noisy and heterogeneous clinical data. We propose a retrieval-augmented learning framework that leverages historical FAERS reports to construct evidence-enriched training instances for ADR severity prediction. Each ADR query, including patient demographics, drug exposure, and indications, is encoded using a fine-tuned BGE-M3 embedding model. We retrieve the top five relevant cases using BM25 lexical search and the top five semantically similar cases using dense vector search, and fuse them via an attention-based aggregation mechanism to produce retrieval-aware representations. These representations are evaluated using machine learning, deep learning, transformer, and fine-tuned large language model approaches for binary severity prediction. Results show that a tree-based ensemble achieves the best performance with an AUC of 82.3{\%}, outperforming the strongest deep learning baseline by 2.3 percentage points and fine-tuned LLMs by 17 percentage points. Overall, the findings demonstrate that retrieval-enhanced data preprocessing can improve representation quality for ADR severity prediction, while the proposed upstream data engineering approach enables classical ensemble methods to remain highly effective for large-scale pharmacovigilance risk prediction."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="guo-etal-2026-attention">
<titleInfo>
<title>Attention-Weighted Retrieval-Augmented Data Engineering for ADR Severity Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nishant</namePart>
<namePart type="family">Vishwamitra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kim-Kwang</namePart>
<namePart type="given">Raymond</namePart>
<namePart type="family">Choo</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>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pepa</namePart>
<namePart type="family">Atanasova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gholamreza</namePart>
<namePart type="family">Haffari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minghan</namePart>
<namePart type="family">Wang</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">979-8-89176-460-6</identifier>
</relatedItem>
<abstract>Adverse drug reaction (ADR) severity prediction is a key task in pharmacovigilance and post-market drug safety surveillance, but is of- ten challenged by noisy and heterogeneous clinical data. We propose a retrieval-augmented learning framework that leverages historical FAERS reports to construct evidence-enriched training instances for ADR severity prediction. Each ADR query, including patient demographics, drug exposure, and indications, is encoded using a fine-tuned BGE-M3 embedding model. We retrieve the top five relevant cases using BM25 lexical search and the top five semantically similar cases using dense vector search, and fuse them via an attention-based aggregation mechanism to produce retrieval-aware representations. These representations are evaluated using machine learning, deep learning, transformer, and fine-tuned large language model approaches for binary severity prediction. Results show that a tree-based ensemble achieves the best performance with an AUC of 82.3%, outperforming the strongest deep learning baseline by 2.3 percentage points and fine-tuned LLMs by 17 percentage points. Overall, the findings demonstrate that retrieval-enhanced data preprocessing can improve representation quality for ADR severity prediction, while the proposed upstream data engineering approach enables classical ensemble methods to remain highly effective for large-scale pharmacovigilance risk prediction.</abstract>
<identifier type="citekey">guo-etal-2026-attention</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-industry.131/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>2234</start>
<end>2243</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Attention-Weighted Retrieval-Augmented Data Engineering for ADR Severity Classification
%A Guo, David
%A Vishwamitra, Nishant
%A Choo, Kim-Kwang Raymond
%Y Atanasova, Pepa
%Y Haffari, Gholamreza
%Y Wang, Minghan
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-460-6
%F guo-etal-2026-attention
%X Adverse drug reaction (ADR) severity prediction is a key task in pharmacovigilance and post-market drug safety surveillance, but is of- ten challenged by noisy and heterogeneous clinical data. We propose a retrieval-augmented learning framework that leverages historical FAERS reports to construct evidence-enriched training instances for ADR severity prediction. Each ADR query, including patient demographics, drug exposure, and indications, is encoded using a fine-tuned BGE-M3 embedding model. We retrieve the top five relevant cases using BM25 lexical search and the top five semantically similar cases using dense vector search, and fuse them via an attention-based aggregation mechanism to produce retrieval-aware representations. These representations are evaluated using machine learning, deep learning, transformer, and fine-tuned large language model approaches for binary severity prediction. Results show that a tree-based ensemble achieves the best performance with an AUC of 82.3%, outperforming the strongest deep learning baseline by 2.3 percentage points and fine-tuned LLMs by 17 percentage points. Overall, the findings demonstrate that retrieval-enhanced data preprocessing can improve representation quality for ADR severity prediction, while the proposed upstream data engineering approach enables classical ensemble methods to remain highly effective for large-scale pharmacovigilance risk prediction.
%U https://aclanthology.org/2026.emnlp-industry.131/
%P 2234-2243
Markdown (Informal)
[Attention-Weighted Retrieval-Augmented Data Engineering for ADR Severity Classification](https://aclanthology.org/2026.emnlp-industry.131/) (Guo et al., EMNLP 2026)
ACL