Determining Legal Relevance with LLMs using Relevance Chain Prompting

In legal reasoning, part of determining whether evidence should be admissible in court requires assessing its relevance to the case, often formalized as its probative value---the degree to which its being true or false proves a fact in issue. However, determining probative value is an imprecise proc...

Full description

Saved in:
Bibliographic Details
Main Authors: Onur Bilgin, John Licato
Format: Article
Language:English
Published: LibraryPress@UF 2024-05-01
Series:Proceedings of the International Florida Artificial Intelligence Research Society Conference
Subjects:
Online Access:https://journals.flvc.org/FLAIRS/article/view/135477
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850271203390914560
author Onur Bilgin
John Licato
author_facet Onur Bilgin
John Licato
author_sort Onur Bilgin
collection DOAJ
description In legal reasoning, part of determining whether evidence should be admissible in court requires assessing its relevance to the case, often formalized as its probative value---the degree to which its being true or false proves a fact in issue. However, determining probative value is an imprecise process and must often rely on consideration of arguments for and against the probative value of a fact. Can generative language models be of use in generating or assessing such arguments? In this work, we introduce relevance chain prompting, a new prompting method that enables large language models to reason about the relevance of evidence to a given fact and uses measures of chain strength. We explore different methods for scoring a relevance chain grounded in the idea of probative value. Additionally, we evaluate the outputs of large language models with ROSCOE metrics and compare the results to chain-of-thought prompting. We test the prompting methods on a dataset created from the Legal Evidence Retrieval dataset. After postprocessing with the ROSCOE metrics, our method outperforms chain-of-thought prompting.
format Article
id doaj-art-2ea25372ab1346668e782a8f5c31af2f
institution OA Journals
issn 2334-0754
2334-0762
language English
publishDate 2024-05-01
publisher LibraryPress@UF
record_format Article
series Proceedings of the International Florida Artificial Intelligence Research Society Conference
spelling doaj-art-2ea25372ab1346668e782a8f5c31af2f2025-08-20T01:52:19ZengLibraryPress@UFProceedings of the International Florida Artificial Intelligence Research Society Conference2334-07542334-07622024-05-013710.32473/flairs.37.1.13547771850Determining Legal Relevance with LLMs using Relevance Chain PromptingOnur Bilgin0https://orcid.org/0009-0002-1690-4779John Licato1Department of Computer Science and Engineering, University of South FloridaDepartment of Computer Science and Engineering, University of South FloridaIn legal reasoning, part of determining whether evidence should be admissible in court requires assessing its relevance to the case, often formalized as its probative value---the degree to which its being true or false proves a fact in issue. However, determining probative value is an imprecise process and must often rely on consideration of arguments for and against the probative value of a fact. Can generative language models be of use in generating or assessing such arguments? In this work, we introduce relevance chain prompting, a new prompting method that enables large language models to reason about the relevance of evidence to a given fact and uses measures of chain strength. We explore different methods for scoring a relevance chain grounded in the idea of probative value. Additionally, we evaluate the outputs of large language models with ROSCOE metrics and compare the results to chain-of-thought prompting. We test the prompting methods on a dataset created from the Legal Evidence Retrieval dataset. After postprocessing with the ROSCOE metrics, our method outperforms chain-of-thought prompting.https://journals.flvc.org/FLAIRS/article/view/135477relevance-chainlegal relevanceprobative valuelegal evidence retrieval
spellingShingle Onur Bilgin
John Licato
Determining Legal Relevance with LLMs using Relevance Chain Prompting
Proceedings of the International Florida Artificial Intelligence Research Society Conference
relevance-chain
legal relevance
probative value
legal evidence retrieval
title Determining Legal Relevance with LLMs using Relevance Chain Prompting
title_full Determining Legal Relevance with LLMs using Relevance Chain Prompting
title_fullStr Determining Legal Relevance with LLMs using Relevance Chain Prompting
title_full_unstemmed Determining Legal Relevance with LLMs using Relevance Chain Prompting
title_short Determining Legal Relevance with LLMs using Relevance Chain Prompting
title_sort determining legal relevance with llms using relevance chain prompting
topic relevance-chain
legal relevance
probative value
legal evidence retrieval
url https://journals.flvc.org/FLAIRS/article/view/135477
work_keys_str_mv AT onurbilgin determininglegalrelevancewithllmsusingrelevancechainprompting
AT johnlicato determininglegalrelevancewithllmsusingrelevancechainprompting