@inproceedings{biswas-anish-2026-multi,
title = "Multi-View Contract Graph: A Knowledge Graph-Based Retrieval Framework for Contract Information Extraction",
author = "Biswas, Momojit and
Anish, Preethu Rose",
editor = "Er-Rahmadi, Btissam and
Montella, S{\'e}bastien and
Graux, Damien and
Melo, Andr{\'e} and
Jabeen, Hajira",
booktitle = "Proceedings of the 3rd Workshop on {KNO}wledge {GR}aphs Agentic Systems Interplay ({NORA} 2026)",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.nora-1.5/",
pages = "53--62",
ISBN = "979-8-89176-457-6",
abstract = "Legal contract understanding often requires connecting information distributed across multiple clauses and cross-referenced provisions. While Retrieval-Augmented Generation (RAG) grounds Large Language Models (LLMs) in relevant evidence, conventional retrieval primarily prioritizes direct query relevance and may overlook supporting contractual context. We propose the Multi-View Contract Graph (MCG), a contract-specific knowledge graph that models semantic, entity, keyword, and structural relationships among clauses. By traversing these relationships, MCG retrieves supporting evidence that may not directly match the query but is necessary for accurate interpretation. We evaluate MCG on the Contract Understanding Atticus Dataset (CUAD), covering 15 information categories, including audit rights, governing laws, and liability-related provisions. Across five open-source LLMs, MCG consistently outperforms traditional retrieval, achieving a best $F_{1}$ score of 0.460 with Mistral-7B-Instruct-v0.3. Compared with BM25-RAG and ColBERT-RAG, the best MCG configuration improves $F_{1}$ by approximately 10.0{\%} and 12.2{\%}, respectively. These results demonstrate that modeling clause-level relationships improves retrieval and information extraction for legal contracts."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="biswas-anish-2026-multi">
<titleInfo>
<title>Multi-View Contract Graph: A Knowledge Graph-Based Retrieval Framework for Contract Information Extraction</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">Preethu</namePart>
<namePart type="given">Rose</namePart>
<namePart type="family">Anish</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 3rd Workshop on KNOwledge GRaphs Agentic Systems Interplay (NORA 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Btissam</namePart>
<namePart type="family">Er-Rahmadi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sébastien</namePart>
<namePart type="family">Montella</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Damien</namePart>
<namePart type="family">Graux</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">André</namePart>
<namePart type="family">Melo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hajira</namePart>
<namePart type="family">Jabeen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-457-6</identifier>
</relatedItem>
<abstract>Legal contract understanding often requires connecting information distributed across multiple clauses and cross-referenced provisions. While Retrieval-Augmented Generation (RAG) grounds Large Language Models (LLMs) in relevant evidence, conventional retrieval primarily prioritizes direct query relevance and may overlook supporting contractual context. We propose the Multi-View Contract Graph (MCG), a contract-specific knowledge graph that models semantic, entity, keyword, and structural relationships among clauses. By traversing these relationships, MCG retrieves supporting evidence that may not directly match the query but is necessary for accurate interpretation. We evaluate MCG on the Contract Understanding Atticus Dataset (CUAD), covering 15 information categories, including audit rights, governing laws, and liability-related provisions. Across five open-source LLMs, MCG consistently outperforms traditional retrieval, achieving a best F₁ score of 0.460 with Mistral-7B-Instruct-v0.3. Compared with BM25-RAG and ColBERT-RAG, the best MCG configuration improves F₁ by approximately 10.0% and 12.2%, respectively. These results demonstrate that modeling clause-level relationships improves retrieval and information extraction for legal contracts.</abstract>
<identifier type="citekey">biswas-anish-2026-multi</identifier>
<location>
<url>https://aclanthology.org/2026.nora-1.5/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>53</start>
<end>62</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multi-View Contract Graph: A Knowledge Graph-Based Retrieval Framework for Contract Information Extraction
%A Biswas, Momojit
%A Anish, Preethu Rose
%Y Er-Rahmadi, Btissam
%Y Montella, Sébastien
%Y Graux, Damien
%Y Melo, André
%Y Jabeen, Hajira
%S Proceedings of the 3rd Workshop on KNOwledge GRaphs Agentic Systems Interplay (NORA 2026)
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-457-6
%F biswas-anish-2026-multi
%X Legal contract understanding often requires connecting information distributed across multiple clauses and cross-referenced provisions. While Retrieval-Augmented Generation (RAG) grounds Large Language Models (LLMs) in relevant evidence, conventional retrieval primarily prioritizes direct query relevance and may overlook supporting contractual context. We propose the Multi-View Contract Graph (MCG), a contract-specific knowledge graph that models semantic, entity, keyword, and structural relationships among clauses. By traversing these relationships, MCG retrieves supporting evidence that may not directly match the query but is necessary for accurate interpretation. We evaluate MCG on the Contract Understanding Atticus Dataset (CUAD), covering 15 information categories, including audit rights, governing laws, and liability-related provisions. Across five open-source LLMs, MCG consistently outperforms traditional retrieval, achieving a best F₁ score of 0.460 with Mistral-7B-Instruct-v0.3. Compared with BM25-RAG and ColBERT-RAG, the best MCG configuration improves F₁ by approximately 10.0% and 12.2%, respectively. These results demonstrate that modeling clause-level relationships improves retrieval and information extraction for legal contracts.
%U https://aclanthology.org/2026.nora-1.5/
%P 53-62
Markdown (Informal)
[Multi-View Contract Graph: A Knowledge Graph-Based Retrieval Framework for Contract Information Extraction](https://aclanthology.org/2026.nora-1.5/) (Biswas & Anish, NORA 2026)
ACL