@inproceedings{maity-etal-2026-a3s,
title = "{A}3{S}@{C}-{DAC} at {\#}{SMM}4{H}-{H}ea{RD} 2026: Reasoning Meets Evidence: {LLM}s for Interpretable Insomnia Detection with Evidence Extraction in Clinical Notes",
author = "Maity, Abhishek and
Shinde, Amol and
Kushare, Abhishek Suresh and
Pawar, Swapnil",
editor = "Lopez-Garcia, Guillermo and
Gonzalez-Hernandez, Graciela",
booktitle = "Proceedings of the 11th Social Media Mining for Health Research and Applications ({SMM}4{H}-{H}ea{RD} 2026) Workshop and Shared Tasks",
month = jul,
year = "2026",
address = "San Diego, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.smm4h-1.1/",
pages = "1--6",
ISBN = "979-8-89176-432-3",
abstract = "Detecting insomnia from clinical narratives requires both accurate classification and clinically grounded reasoning with interpretable evidence. We present our systems for the SMM4H-HeaRD 2026 shared task, which leverages MIMIC-III notes annotated with rule-based insomnia criteria and supporting evidence spans. We explore two complementary approaches: parameter-efficient fine-tuning of lightweight models using QLoRA and LoRA, and few-shot prompting of large language models for joint reasoning and evidence extraction. Our best system achieves an F1-score of 0.7333 on binary classification and a micro-F1 of 0.6535 on multi-label rule prediction, with up to 0.5192 partial-match F1 for evidence extraction. Results show that lightweight fine-tuned models can outperform larger models in classification, while larger models demonstrate stronger reasoning but struggle with precise span localization, highlighting a key gap in clinically interpretable NLP systems."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="maity-etal-2026-a3s">
<titleInfo>
<title>A3S@C-DAC at #SMM4H-HeaRD 2026: Reasoning Meets Evidence: LLMs for Interpretable Insomnia Detection with Evidence Extraction in Clinical Notes</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abhishek</namePart>
<namePart type="family">Maity</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amol</namePart>
<namePart type="family">Shinde</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abhishek</namePart>
<namePart type="given">Suresh</namePart>
<namePart type="family">Kushare</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Swapnil</namePart>
<namePart type="family">Pawar</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 11th Social Media Mining for Health Research and Applications (SMM4H-HeaRD 2026) Workshop and Shared Tasks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Guillermo</namePart>
<namePart type="family">Lopez-Garcia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Graciela</namePart>
<namePart type="family">Gonzalez-Hernandez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-432-3</identifier>
</relatedItem>
<abstract>Detecting insomnia from clinical narratives requires both accurate classification and clinically grounded reasoning with interpretable evidence. We present our systems for the SMM4H-HeaRD 2026 shared task, which leverages MIMIC-III notes annotated with rule-based insomnia criteria and supporting evidence spans. We explore two complementary approaches: parameter-efficient fine-tuning of lightweight models using QLoRA and LoRA, and few-shot prompting of large language models for joint reasoning and evidence extraction. Our best system achieves an F1-score of 0.7333 on binary classification and a micro-F1 of 0.6535 on multi-label rule prediction, with up to 0.5192 partial-match F1 for evidence extraction. Results show that lightweight fine-tuned models can outperform larger models in classification, while larger models demonstrate stronger reasoning but struggle with precise span localization, highlighting a key gap in clinically interpretable NLP systems.</abstract>
<identifier type="citekey">maity-etal-2026-a3s</identifier>
<location>
<url>https://aclanthology.org/2026.smm4h-1.1/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>1</start>
<end>6</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A3S@C-DAC at #SMM4H-HeaRD 2026: Reasoning Meets Evidence: LLMs for Interpretable Insomnia Detection with Evidence Extraction in Clinical Notes
%A Maity, Abhishek
%A Shinde, Amol
%A Kushare, Abhishek Suresh
%A Pawar, Swapnil
%Y Lopez-Garcia, Guillermo
%Y Gonzalez-Hernandez, Graciela
%S Proceedings of the 11th Social Media Mining for Health Research and Applications (SMM4H-HeaRD 2026) Workshop and Shared Tasks
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, United States
%@ 979-8-89176-432-3
%F maity-etal-2026-a3s
%X Detecting insomnia from clinical narratives requires both accurate classification and clinically grounded reasoning with interpretable evidence. We present our systems for the SMM4H-HeaRD 2026 shared task, which leverages MIMIC-III notes annotated with rule-based insomnia criteria and supporting evidence spans. We explore two complementary approaches: parameter-efficient fine-tuning of lightweight models using QLoRA and LoRA, and few-shot prompting of large language models for joint reasoning and evidence extraction. Our best system achieves an F1-score of 0.7333 on binary classification and a micro-F1 of 0.6535 on multi-label rule prediction, with up to 0.5192 partial-match F1 for evidence extraction. Results show that lightweight fine-tuned models can outperform larger models in classification, while larger models demonstrate stronger reasoning but struggle with precise span localization, highlighting a key gap in clinically interpretable NLP systems.
%U https://aclanthology.org/2026.smm4h-1.1/
%P 1-6
Markdown (Informal)
[A3S@C-DAC at #SMM4H-HeaRD 2026: Reasoning Meets Evidence: LLMs for Interpretable Insomnia Detection with Evidence Extraction in Clinical Notes](https://aclanthology.org/2026.smm4h-1.1/) (Maity et al., SMM4H 2026)
ACL