Using LLMs to Automate and Audit Business Contracts

This literature review examines the current state of research on the use of Large Language Models (LLMs) for automating and auditing business contracts, with an emphasis on their applications in legal compliance and risk management. By analysing existing studies, the review highlights the capabilities of LLMs in classifying, interpreting, and validating contract clauses, as well as the challenges related to accuracy, data diversity, and integration into legal workflows. The review identifies gaps in knowledge and methodology, such as limited evaluation of multi-jurisdictional adaptability and real-time performance. It also discusses advancements in natural language processing techniques that could improve clause classification precision. The findings suggest that while LLMs hold promise for improving contract analysis efficiency and risk mitigation, further empirical research is needed to validate their effectiveness across diverse legal contexts. This review provides a foundation for future investigations aiming to enhance the deployment of LLMs in legal and compliance settings.

Publication Details

Journal
Figshare
Published
2025-01-01
DOI
https://doi.org/10.6084/m9.figshare.29693390.v1
Primary Topic
Artificial Intelligence in Law
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Using LLMs to Automate and Audit Business Contracts

Figshare
Artificial Intelligence in Law
article

Using LLMs to Automate and Audit Business Contracts

article en

Abstract

This literature review examines the current state of research on the use of Large Language Models (LLMs) for automating and auditing business contracts, with an emphasis on their applications in legal compliance and risk management. By analysing existing studies, the review highlights the capabilities of LLMs in classifying, interpreting, and validating contract clauses, as well as the challenges related to accuracy, data diversity, and integration into legal workflows. The review identifies gaps in knowledge and methodology, such as limited evaluation of multi-jurisdictional adaptability and real-time performance. It also discusses advancements in natural language processing techniques that could improve clause classification precision. The findings suggest that while LLMs hold promise for improving contract analysis efficiency and risk mitigation, further empirical research is needed to validate their effectiveness across diverse legal contexts. This review provides a foundation for future investigations aiming to enhance the deployment of LLMs in legal and compliance settings.

Figshare
Openalex Percentile: Top 53%
Artificial Intelligence in Law
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.