@inproceedings{biswas-etal-2026-mitigating,
title = "Mitigating Misinterpretation in Policy Documents through Automated Language Understanding",
author = "Biswas, Momojit and
Tummepalli, Anka Chandrahas and
Anish, Preethu Rose",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.651/",
doi = "10.63317/32bvjtupxb64",
pages = "8217--8234",
abstract = "Policy documents often employ intricate and technical language, posing comprehension challenges for policyholders and increasing the risk of misinterpretation, financial losses, and legal disputes. To address these issues, we propose an automated framework leveraging Retrieval-Augmented Generation to identify and clarify potentially mis-interpretable paragraphs within policy documents. The framework consists of two key modules: the Annotation module and the Rectification module. The Annotation module employs both paragraph-level and document-level contextual reasoning to classify paragraphs into categories indicative of potential misinterpretation. The Rectification module resolves these ambiguities by generating targeted interpretation queries, retrieving relevant document-level context, and incorporating external knowledge sources. Applied to a corpus of 240 real-world policy documents, the Annotation module produced a benchmark dataset comprising 11,000 annotated paragraphs, enabling systematic evaluation of interpretability issues. We assessed the dataset{'}s quality through expert-driven manual reviews and large-scale automated evaluations using fine-tuned Pretrained Language Model. For the Rectification module, we evaluated five open-source Large Language Models: Mistral-2-7B, Mistral-3-7B, LLaMA-2-7B, LLaMA-3-8B, andSaul-7B. Among these, Mistral-2-7B achieved the highest human evaluation scores: 0.912 for Clarity, 0.914 for Fidelity, and 0.934 for Usefulness. This work demonstrates the practical feasibility of utilizing automated frameworks to enhance the clarity and comprehensibility of complex policy documents, thereby mitigating risks associated with misinterpretation and its adverse consequences."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="biswas-etal-2026-mitigating">
<titleInfo>
<title>Mitigating Misinterpretation in Policy Documents through Automated Language Understanding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Momojit</namePart>
<namePart type="family">Biswas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anka</namePart>
<namePart type="given">Chandrahas</namePart>
<namePart type="family">Tummepalli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preethu</namePart>
<namePart type="given">Rose</namePart>
<namePart type="family">Anish</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Policy documents often employ intricate and technical language, posing comprehension challenges for policyholders and increasing the risk of misinterpretation, financial losses, and legal disputes. To address these issues, we propose an automated framework leveraging Retrieval-Augmented Generation to identify and clarify potentially mis-interpretable paragraphs within policy documents. The framework consists of two key modules: the Annotation module and the Rectification module. The Annotation module employs both paragraph-level and document-level contextual reasoning to classify paragraphs into categories indicative of potential misinterpretation. The Rectification module resolves these ambiguities by generating targeted interpretation queries, retrieving relevant document-level context, and incorporating external knowledge sources. Applied to a corpus of 240 real-world policy documents, the Annotation module produced a benchmark dataset comprising 11,000 annotated paragraphs, enabling systematic evaluation of interpretability issues. We assessed the dataset’s quality through expert-driven manual reviews and large-scale automated evaluations using fine-tuned Pretrained Language Model. For the Rectification module, we evaluated five open-source Large Language Models: Mistral-2-7B, Mistral-3-7B, LLaMA-2-7B, LLaMA-3-8B, andSaul-7B. Among these, Mistral-2-7B achieved the highest human evaluation scores: 0.912 for Clarity, 0.914 for Fidelity, and 0.934 for Usefulness. This work demonstrates the practical feasibility of utilizing automated frameworks to enhance the clarity and comprehensibility of complex policy documents, thereby mitigating risks associated with misinterpretation and its adverse consequences.</abstract>
<identifier type="citekey">biswas-etal-2026-mitigating</identifier>
<identifier type="doi">10.63317/32bvjtupxb64</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.651/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>8217</start>
<end>8234</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Mitigating Misinterpretation in Policy Documents through Automated Language Understanding
%A Biswas, Momojit
%A Tummepalli, Anka Chandrahas
%A Anish, Preethu Rose
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F biswas-etal-2026-mitigating
%X Policy documents often employ intricate and technical language, posing comprehension challenges for policyholders and increasing the risk of misinterpretation, financial losses, and legal disputes. To address these issues, we propose an automated framework leveraging Retrieval-Augmented Generation to identify and clarify potentially mis-interpretable paragraphs within policy documents. The framework consists of two key modules: the Annotation module and the Rectification module. The Annotation module employs both paragraph-level and document-level contextual reasoning to classify paragraphs into categories indicative of potential misinterpretation. The Rectification module resolves these ambiguities by generating targeted interpretation queries, retrieving relevant document-level context, and incorporating external knowledge sources. Applied to a corpus of 240 real-world policy documents, the Annotation module produced a benchmark dataset comprising 11,000 annotated paragraphs, enabling systematic evaluation of interpretability issues. We assessed the dataset’s quality through expert-driven manual reviews and large-scale automated evaluations using fine-tuned Pretrained Language Model. For the Rectification module, we evaluated five open-source Large Language Models: Mistral-2-7B, Mistral-3-7B, LLaMA-2-7B, LLaMA-3-8B, andSaul-7B. Among these, Mistral-2-7B achieved the highest human evaluation scores: 0.912 for Clarity, 0.914 for Fidelity, and 0.934 for Usefulness. This work demonstrates the practical feasibility of utilizing automated frameworks to enhance the clarity and comprehensibility of complex policy documents, thereby mitigating risks associated with misinterpretation and its adverse consequences.
%R 10.63317/32bvjtupxb64
%U https://aclanthology.org/2026.lrec-1.651/
%U https://doi.org/10.63317/32bvjtupxb64
%P 8217-8234
Markdown (Informal)
[Mitigating Misinterpretation in Policy Documents through Automated Language Understanding](https://aclanthology.org/2026.lrec-1.651/) (Biswas et al., LREC 2026)
ACL