@inproceedings{ranjit-etal-2026-uncovering,
title = "Uncovering Intervention Opportunities for Suicide Prevention with Language Model Assistants",
author = "Ranjit, Jaspreet and
Cho, Hyundong Justin and
Smerdon, Claire J. and
Nam, Yoonsoo and
Phung, Myles and
May, Jonathan and
Blosnich, John R. and
Swayamdipta, Swabha",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-long.688/",
pages = "15072--15092",
ISBN = "979-8-89176-390-6",
abstract = "The National Violent Death Reporting System (NVDRS) documents suicides in the United States. In a demanding public health data pipeline, annotators manually extract structured information from death investigation records following extensive codebooks (i.e. annotation guidelines) painstakingly developed by experts. In this work, we facilitate data-driven insights from the NVDRS data to support the development of novel suicide interventions by leveraging language models (LM) as assistants to these (a) data annotators and (b) experts. We find that LM predictions match existing data annotations about 85{\%} of the time across 50 NVDRS variables. Where the LM disagrees with existing annotations, our expert review identifies that 38{\%} of these instances reveal inconsistencies between narratives and structured data. Finally, we introduce a human-in-the-loop algorithm that helps experts efficiently build and refine codebooks for new variables by having them only focus on providing feedback for incorrect LM predictions. We apply our algorithm to a real-world case study, and find that about 96K narratives contain evidence of victim interactions with legal professionals, which surfaces a substantial opportunity for upstream intervention that is not captured in the original structured data. Our findings provide evidence that LMs can serve as effective assistants to public health researchers who handle sensitive data in high-stakes scenarios."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ranjit-etal-2026-uncovering">
<titleInfo>
<title>Uncovering Intervention Opportunities for Suicide Prevention with Language Model Assistants</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jaspreet</namePart>
<namePart type="family">Ranjit</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hyundong</namePart>
<namePart type="given">Justin</namePart>
<namePart type="family">Cho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claire</namePart>
<namePart type="given">J</namePart>
<namePart type="family">Smerdon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yoonsoo</namePart>
<namePart type="family">Nam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Myles</namePart>
<namePart type="family">Phung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="family">May</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="given">R</namePart>
<namePart type="family">Blosnich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Swabha</namePart>
<namePart type="family">Swayamdipta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-390-6</identifier>
</relatedItem>
<abstract>The National Violent Death Reporting System (NVDRS) documents suicides in the United States. In a demanding public health data pipeline, annotators manually extract structured information from death investigation records following extensive codebooks (i.e. annotation guidelines) painstakingly developed by experts. In this work, we facilitate data-driven insights from the NVDRS data to support the development of novel suicide interventions by leveraging language models (LM) as assistants to these (a) data annotators and (b) experts. We find that LM predictions match existing data annotations about 85% of the time across 50 NVDRS variables. Where the LM disagrees with existing annotations, our expert review identifies that 38% of these instances reveal inconsistencies between narratives and structured data. Finally, we introduce a human-in-the-loop algorithm that helps experts efficiently build and refine codebooks for new variables by having them only focus on providing feedback for incorrect LM predictions. We apply our algorithm to a real-world case study, and find that about 96K narratives contain evidence of victim interactions with legal professionals, which surfaces a substantial opportunity for upstream intervention that is not captured in the original structured data. Our findings provide evidence that LMs can serve as effective assistants to public health researchers who handle sensitive data in high-stakes scenarios.</abstract>
<identifier type="citekey">ranjit-etal-2026-uncovering</identifier>
<location>
<url>https://aclanthology.org/2026.acl-long.688/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>15072</start>
<end>15092</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Uncovering Intervention Opportunities for Suicide Prevention with Language Model Assistants
%A Ranjit, Jaspreet
%A Cho, Hyundong Justin
%A Smerdon, Claire J.
%A Nam, Yoonsoo
%A Phung, Myles
%A May, Jonathan
%A Blosnich, John R.
%A Swayamdipta, Swabha
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-390-6
%F ranjit-etal-2026-uncovering
%X The National Violent Death Reporting System (NVDRS) documents suicides in the United States. In a demanding public health data pipeline, annotators manually extract structured information from death investigation records following extensive codebooks (i.e. annotation guidelines) painstakingly developed by experts. In this work, we facilitate data-driven insights from the NVDRS data to support the development of novel suicide interventions by leveraging language models (LM) as assistants to these (a) data annotators and (b) experts. We find that LM predictions match existing data annotations about 85% of the time across 50 NVDRS variables. Where the LM disagrees with existing annotations, our expert review identifies that 38% of these instances reveal inconsistencies between narratives and structured data. Finally, we introduce a human-in-the-loop algorithm that helps experts efficiently build and refine codebooks for new variables by having them only focus on providing feedback for incorrect LM predictions. We apply our algorithm to a real-world case study, and find that about 96K narratives contain evidence of victim interactions with legal professionals, which surfaces a substantial opportunity for upstream intervention that is not captured in the original structured data. Our findings provide evidence that LMs can serve as effective assistants to public health researchers who handle sensitive data in high-stakes scenarios.
%U https://aclanthology.org/2026.acl-long.688/
%P 15072-15092
Markdown (Informal)
[Uncovering Intervention Opportunities for Suicide Prevention with Language Model Assistants](https://aclanthology.org/2026.acl-long.688/) (Ranjit et al., ACL 2026)
ACL
- Jaspreet Ranjit, Hyundong Justin Cho, Claire J. Smerdon, Yoonsoo Nam, Myles Phung, Jonathan May, John R. Blosnich, and Swabha Swayamdipta. 2026. Uncovering Intervention Opportunities for Suicide Prevention with Language Model Assistants. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 15072–15092, San Diego, California, United States. Association for Computational Linguistics.