@inproceedings{arun-etal-2026-llms,
title = "{LLM}s and Reasoning in Health Insurance Policy Documents: A Dataset and Argument Graph Extraction Study",
author = "Arun, Govind and
Krishna, Sidharth N and
Rao, Susie Xi and
George, Ajo Babu",
editor = "T.Y.S.S., Santosh and
Agarwal, Amit and
Gupta, Vivek and
Kementchedjhieva, Yova and
Garimella, Aparna and
Hou, Yufang",
booktitle = "The Proceedings of Workshop on Document Intelligence and Understanding",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.docinsights-1.11/",
pages = "155--162",
ISBN = "979-8-89176-477-4",
abstract = "Health insurance policy documents justify coverage decisions through clinical evidence and regulatory criteria, but the underlying reasoning is buried in dense medical and legal text. A pipeline is presented that extracts argument components and relations from these documents and assembles them into directed argument graphs. A dataset of 5,230 sentences and 5,685 relations across 53 documents from Aetna, CMS, and United Healthcare is constructed along with two custom annotation tools. Six classical baselines, three fine-tuned transformer models, and three instruction-tuned LLMs are evaluated, with the LLMs assessed under zero-shot, few-shot, and chain-of-thought prompting. PubMedBERT and Legal-BERT, fine-tuned on the dataset, achieve the strongest results overall (0.731 and 0.653 Macro F1 on component classification and relation extraction, respectively). Notably, the much simpler TF-IDF + SVM baseline is competitive with these fine-tuned transformers (0.709 and 0.649 Macro F1) and outperforms the best prompted LLM by 12 and 21 F1 points respectively. The dataset and code are available at https://anonymous.4open.science/r/LLM-Driven-Argument-Mapping-3ACB/README.md"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="arun-etal-2026-llms">
<titleInfo>
<title>LLMs and Reasoning in Health Insurance Policy Documents: A Dataset and Argument Graph Extraction Study</title>
</titleInfo>
<name type="personal">
<namePart type="given">Govind</namePart>
<namePart type="family">Arun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sidharth</namePart>
<namePart type="given">N</namePart>
<namePart type="family">Krishna</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Susie</namePart>
<namePart type="given">Xi</namePart>
<namePart type="family">Rao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ajo</namePart>
<namePart type="given">Babu</namePart>
<namePart type="family">George</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>The Proceedings of Workshop on Document Intelligence and Understanding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Santosh</namePart>
<namePart type="family">T.Y.S.S.</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amit</namePart>
<namePart type="family">Agarwal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yova</namePart>
<namePart type="family">Kementchedjhieva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aparna</namePart>
<namePart type="family">Garimella</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yufang</namePart>
<namePart type="family">Hou</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">979-8-89176-477-4</identifier>
</relatedItem>
<abstract>Health insurance policy documents justify coverage decisions through clinical evidence and regulatory criteria, but the underlying reasoning is buried in dense medical and legal text. A pipeline is presented that extracts argument components and relations from these documents and assembles them into directed argument graphs. A dataset of 5,230 sentences and 5,685 relations across 53 documents from Aetna, CMS, and United Healthcare is constructed along with two custom annotation tools. Six classical baselines, three fine-tuned transformer models, and three instruction-tuned LLMs are evaluated, with the LLMs assessed under zero-shot, few-shot, and chain-of-thought prompting. PubMedBERT and Legal-BERT, fine-tuned on the dataset, achieve the strongest results overall (0.731 and 0.653 Macro F1 on component classification and relation extraction, respectively). Notably, the much simpler TF-IDF + SVM baseline is competitive with these fine-tuned transformers (0.709 and 0.649 Macro F1) and outperforms the best prompted LLM by 12 and 21 F1 points respectively. The dataset and code are available at https://anonymous.4open.science/r/LLM-Driven-Argument-Mapping-3ACB/README.md</abstract>
<identifier type="citekey">arun-etal-2026-llms</identifier>
<location>
<url>https://aclanthology.org/2026.docinsights-1.11/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>155</start>
<end>162</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LLMs and Reasoning in Health Insurance Policy Documents: A Dataset and Argument Graph Extraction Study
%A Arun, Govind
%A Krishna, Sidharth N.
%A Rao, Susie Xi
%A George, Ajo Babu
%Y T.Y.S.S., Santosh
%Y Agarwal, Amit
%Y Gupta, Vivek
%Y Kementchedjhieva, Yova
%Y Garimella, Aparna
%Y Hou, Yufang
%S The Proceedings of Workshop on Document Intelligence and Understanding
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-477-4
%F arun-etal-2026-llms
%X Health insurance policy documents justify coverage decisions through clinical evidence and regulatory criteria, but the underlying reasoning is buried in dense medical and legal text. A pipeline is presented that extracts argument components and relations from these documents and assembles them into directed argument graphs. A dataset of 5,230 sentences and 5,685 relations across 53 documents from Aetna, CMS, and United Healthcare is constructed along with two custom annotation tools. Six classical baselines, three fine-tuned transformer models, and three instruction-tuned LLMs are evaluated, with the LLMs assessed under zero-shot, few-shot, and chain-of-thought prompting. PubMedBERT and Legal-BERT, fine-tuned on the dataset, achieve the strongest results overall (0.731 and 0.653 Macro F1 on component classification and relation extraction, respectively). Notably, the much simpler TF-IDF + SVM baseline is competitive with these fine-tuned transformers (0.709 and 0.649 Macro F1) and outperforms the best prompted LLM by 12 and 21 F1 points respectively. The dataset and code are available at https://anonymous.4open.science/r/LLM-Driven-Argument-Mapping-3ACB/README.md
%U https://aclanthology.org/2026.docinsights-1.11/
%P 155-162
Markdown (Informal)
[LLMs and Reasoning in Health Insurance Policy Documents: A Dataset and Argument Graph Extraction Study](https://aclanthology.org/2026.docinsights-1.11/) (Arun et al., DocInsights 2026)
ACL