@inproceedings{wang-etal-2026-harmreduction,
title = "{H}arm{R}eduction: Benchmarking {LLM}s in Harm Reduction Information Provision to Support People Who Use Drugs",
author = "Wang, Kaixuan and
Diao, Chenxin and
Jacques, Jason T. and
Guo, Zhongliang and
Clarke, Loraine and
Zhao, Shuai",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.280/",
pages = "6382--6400",
ISBN = "979-8-89176-459-0",
abstract = "Millions of individuals' well-being are challenged by the harms of substance use. Harm reduction as a public health strategy provides non-judgemental, evidence-based information intended to improve health outcomes and reduce associated safety risks. Some large language models (LLMs) have demonstrated a high level of medical reasoning, promising to address the information needs of people who use drugs (PWUD). However, their performance in relevant tasks remains largely unexplored. We introduce HarmReduction, a benchmark designed to evaluate LLMs' accuracy and safety risks in harm reduction information provision. The benchmark dataset (HRBasic) has 2,160 question-answer-evidence pairs. The scope covers three tasks: checking safety boundaries, providing quantitative values, and inferring polysubstance use risks. We build the Instruction and RAG schemes to evaluate model behaviours based on their inherent knowledge and the integration of domain knowledge. Our results indicate that state-of-the-art LLMs still struggle to provide accurate harm reduction information, and sometimes, present severe safety risks to PWUD. This work contributes an evaluation framework for LLMs to deliver harm reduction information to avoid introducing negative health outcomes through the use of LLMs."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2026-harmreduction">
<titleInfo>
<title>HarmReduction: Benchmarking LLMs in Harm Reduction Information Provision to Support People Who Use Drugs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kaixuan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenxin</namePart>
<namePart type="family">Diao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jason</namePart>
<namePart type="given">T</namePart>
<namePart type="family">Jacques</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhongliang</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Loraine</namePart>
<namePart type="family">Clarke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuai</namePart>
<namePart type="family">Zhao</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</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">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>Millions of individuals’ well-being are challenged by the harms of substance use. Harm reduction as a public health strategy provides non-judgemental, evidence-based information intended to improve health outcomes and reduce associated safety risks. Some large language models (LLMs) have demonstrated a high level of medical reasoning, promising to address the information needs of people who use drugs (PWUD). However, their performance in relevant tasks remains largely unexplored. We introduce HarmReduction, a benchmark designed to evaluate LLMs’ accuracy and safety risks in harm reduction information provision. The benchmark dataset (HRBasic) has 2,160 question-answer-evidence pairs. The scope covers three tasks: checking safety boundaries, providing quantitative values, and inferring polysubstance use risks. We build the Instruction and RAG schemes to evaluate model behaviours based on their inherent knowledge and the integration of domain knowledge. Our results indicate that state-of-the-art LLMs still struggle to provide accurate harm reduction information, and sometimes, present severe safety risks to PWUD. This work contributes an evaluation framework for LLMs to deliver harm reduction information to avoid introducing negative health outcomes through the use of LLMs.</abstract>
<identifier type="citekey">wang-etal-2026-harmreduction</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.280/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>6382</start>
<end>6400</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T HarmReduction: Benchmarking LLMs in Harm Reduction Information Provision to Support People Who Use Drugs
%A Wang, Kaixuan
%A Diao, Chenxin
%A Jacques, Jason T.
%A Guo, Zhongliang
%A Clarke, Loraine
%A Zhao, Shuai
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F wang-etal-2026-harmreduction
%X Millions of individuals’ well-being are challenged by the harms of substance use. Harm reduction as a public health strategy provides non-judgemental, evidence-based information intended to improve health outcomes and reduce associated safety risks. Some large language models (LLMs) have demonstrated a high level of medical reasoning, promising to address the information needs of people who use drugs (PWUD). However, their performance in relevant tasks remains largely unexplored. We introduce HarmReduction, a benchmark designed to evaluate LLMs’ accuracy and safety risks in harm reduction information provision. The benchmark dataset (HRBasic) has 2,160 question-answer-evidence pairs. The scope covers three tasks: checking safety boundaries, providing quantitative values, and inferring polysubstance use risks. We build the Instruction and RAG schemes to evaluate model behaviours based on their inherent knowledge and the integration of domain knowledge. Our results indicate that state-of-the-art LLMs still struggle to provide accurate harm reduction information, and sometimes, present severe safety risks to PWUD. This work contributes an evaluation framework for LLMs to deliver harm reduction information to avoid introducing negative health outcomes through the use of LLMs.
%U https://aclanthology.org/2026.emnlp-main.280/
%P 6382-6400
Markdown (Informal)
[HarmReduction: Benchmarking LLMs in Harm Reduction Information Provision to Support People Who Use Drugs](https://aclanthology.org/2026.emnlp-main.280/) (Wang et al., EMNLP 2026)
ACL