@inproceedings{rykov-etal-2026-fine,
title = "Fine-Grained Semantic Comparison of Legal Documents using {LLM}s",
author = "Rykov, Elisei and
Ivanov, Nikolay and
Bandulevich, Maria and
Petrushina, Kseniia and
Malykh, Valentin and
Konovalov, Vasily and
Panchenko, Alexander and
Alimova, Ilseyar",
editor = "T.Y.S.S., Santosh and
Rodriguez, Juan Diego and
de Gibert, Ona",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 4: Student Research Workshop)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-srw.86/",
doi = "10.18653/v1/2026.acl-srw.86",
pages = "982--994",
ISBN = "979-8-89176-393-7",
abstract = "Frequent revisions of complex regulatory documents in large organizations often introduce inconsistencies and contradictions that are difficult for lawyers and auditors to detect manually. Existing tools rely on character-level diffs and therefore miss paraphrases and semantic shifts. We introduce LegDiff, a novel benchmark for evaluating span-aware semantic comparison of legal texts, and use it to investigate the ability of large language models to detect semantic changes beyond token- and character-level matching. LegDiff comprises manually annotated pairs of legal paragraphs drawn from different documents. In addition, we present a pipeline to generate synthetic training data that aligns with the manual annotations and mirrors the structure and label distribution of the manually curated benchmark, and a visualization tool for clearly displaying detected differences and inconsistencies. The dataset, code, and a visualization tool are publicly available to facilitate reproducibility and further research (\url{https://github.com/s-nlp/SLeDoC})."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rykov-etal-2026-fine">
<titleInfo>
<title>Fine-Grained Semantic Comparison of Legal Documents using LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Elisei</namePart>
<namePart type="family">Rykov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikolay</namePart>
<namePart type="family">Ivanov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Bandulevich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kseniia</namePart>
<namePart type="family">Petrushina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Valentin</namePart>
<namePart type="family">Malykh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vasily</namePart>
<namePart type="family">Konovalov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Panchenko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ilseyar</namePart>
<namePart type="family">Alimova</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 4: Student Research Workshop)</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">Juan</namePart>
<namePart type="given">Diego</namePart>
<namePart type="family">Rodriguez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ona</namePart>
<namePart type="family">de Gibert</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">979-8-89176-393-7</identifier>
</relatedItem>
<abstract>Frequent revisions of complex regulatory documents in large organizations often introduce inconsistencies and contradictions that are difficult for lawyers and auditors to detect manually. Existing tools rely on character-level diffs and therefore miss paraphrases and semantic shifts. We introduce LegDiff, a novel benchmark for evaluating span-aware semantic comparison of legal texts, and use it to investigate the ability of large language models to detect semantic changes beyond token- and character-level matching. LegDiff comprises manually annotated pairs of legal paragraphs drawn from different documents. In addition, we present a pipeline to generate synthetic training data that aligns with the manual annotations and mirrors the structure and label distribution of the manually curated benchmark, and a visualization tool for clearly displaying detected differences and inconsistencies. The dataset, code, and a visualization tool are publicly available to facilitate reproducibility and further research (https://github.com/s-nlp/SLeDoC).</abstract>
<identifier type="citekey">rykov-etal-2026-fine</identifier>
<identifier type="doi">10.18653/v1/2026.acl-srw.86</identifier>
<location>
<url>https://aclanthology.org/2026.acl-srw.86/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>982</start>
<end>994</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Fine-Grained Semantic Comparison of Legal Documents using LLMs
%A Rykov, Elisei
%A Ivanov, Nikolay
%A Bandulevich, Maria
%A Petrushina, Kseniia
%A Malykh, Valentin
%A Konovalov, Vasily
%A Panchenko, Alexander
%A Alimova, Ilseyar
%Y T.Y.S.S., Santosh
%Y Rodriguez, Juan Diego
%Y de Gibert, Ona
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-393-7
%F rykov-etal-2026-fine
%X Frequent revisions of complex regulatory documents in large organizations often introduce inconsistencies and contradictions that are difficult for lawyers and auditors to detect manually. Existing tools rely on character-level diffs and therefore miss paraphrases and semantic shifts. We introduce LegDiff, a novel benchmark for evaluating span-aware semantic comparison of legal texts, and use it to investigate the ability of large language models to detect semantic changes beyond token- and character-level matching. LegDiff comprises manually annotated pairs of legal paragraphs drawn from different documents. In addition, we present a pipeline to generate synthetic training data that aligns with the manual annotations and mirrors the structure and label distribution of the manually curated benchmark, and a visualization tool for clearly displaying detected differences and inconsistencies. The dataset, code, and a visualization tool are publicly available to facilitate reproducibility and further research (https://github.com/s-nlp/SLeDoC).
%R 10.18653/v1/2026.acl-srw.86
%U https://aclanthology.org/2026.acl-srw.86/
%U https://doi.org/10.18653/v1/2026.acl-srw.86
%P 982-994
Markdown (Informal)
[Fine-Grained Semantic Comparison of Legal Documents using LLMs](https://aclanthology.org/2026.acl-srw.86/) (Rykov et al., ACL 2026)
ACL
- Elisei Rykov, Nikolay Ivanov, Maria Bandulevich, Kseniia Petrushina, Valentin Malykh, Vasily Konovalov, Alexander Panchenko, and Ilseyar Alimova. 2026. Fine-Grained Semantic Comparison of Legal Documents using LLMs. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop), pages 982–994, San Diego, California, United States. Association for Computational Linguistics.