CRYPTOREPORTCLUB
  • Crypto news
  • AI
  • Technologies
Wednesday, July 2, 2025
No Result
View All Result
CRYPTOREPORTCLUB
  • Crypto news
  • AI
  • Technologies
No Result
View All Result
CRYPTOREPORTCLUB

Retrieve-Revise-Refine: A novel framework for retrieval of concise entailing legal articles

November 27, 2024
155
0

November 27, 2024

Editors' notes

Related Post

Striking parallels between biological brains and AI during social interaction suggest fundamental principles

Striking parallels between biological brains and AI during social interaction suggest fundamental principles

July 2, 2025
Centaur: AI that thinks like us—and could help explain how we think

Centaur: AI that thinks like us—and could help explain how we think

July 2, 2025

This article has been reviewed according to Science X's editorial process and policies. Editors have highlighted the following attributes while ensuring the content's credibility:

fact-checked

trusted source

proofread

Retrieve-Revise-Refine: A novel framework for retrieval of concise entailing legal articles

Retrieve–revise–refine: A novel framework for retrieval of concise entailing legal articles
Overall architecture of Retrieve-Revise-Refine framework. Credit: Information Processing & Management (2024). DOI: 10.1016/j.ipm.2024.103949

Artificial intelligence (AI) continues to redefine the boundaries of legal technology, offering to automate advanced tasks such as legal question answering and consultation. In the domain of statute law, a particular challenge is the task of retrieving the concise set of entailing legal articles to a query. In this context, we refer to this task as entailing legal article set retrieval or, more briefly, legal article set retrieval.

The task of retrieving entailing legal article sets differs markedly from traditional information retrieval (IR) in two main aspects. First, unlike the traditional IR which returns a ranked list of articles, the legal article set retrieval task seeks a concise set of articles. This level of specificity extends to the nature of the legal queries and legal articles themselves: They are inherently complex and steeped in specialized legal language, demanding a retrieval system with deeper legal reasoning and linking capacity.

Second, while traditional IR efforts primarily involve ranking candidates by relevance, our task requires that the retrieved articles not just relate to but jointly entail the contents of a query or its negation. These characteristics set this task apart from the broader goals and methods of traditional IR tasks.

Previous research in legal article set retrieval has predominantly employed two approaches. The first approach combines classical IR models with fine-tuned language models (LMs), and then ensembles the retrieval results to consolidate the final retrieved sets. Meanwhile, the second approach uses classical IR models exclusively for preliminary candidate filtering, which prepares inputs for further LM fine-tuning; the final results are often ensembled from various fine-tuned LMs.

To address the task of legal article retrieval, a team of researchers from the Japan Advanced Institute of Science and Technology (JAIST), led by Professor Le-Minh Nguyen and including doctoral students Chau Nguyen proposed a framework, called Retrieve-Revise-Refine. The framework is designed to pinpoint the concise set of legal articles that either entail a query or its negation, advancing the current understanding of this task.

In addition, their approach leverages the unique advantages of combining both small LMs and large LMs to improve the accuracy of the articles retrieved (i.e., precision), while endeavoring to limit the loss in coverage (i.e., recall). The paper is published in the journal Information Processing & Management.

The framework consists of three stages:

  1. Retrieve: Maximizing the comprehensive retrieval of entailing articles using an ensemble of multiple small LMs, fine-tuned with various tailored strategies.
  2. Revise: Large LMs are utilized to assess the validity of the query with respect to each combination of articles from the top retrieval results, aiming to derive a more compact subset of entailing legal articles.
  3. Refine: Further distilling the outputs from the second stage, using insights derived from the small LMs' predictions as refiners for the predictions of the large LMs.

As shown in the empirical results, their proposed framework achieved state-of-the-art results for the task across two datasets, showing improvements of 3.17% and 4.24%, respectively.

More information: Chau Nguyen et al, Retrieve–Revise–Refine: A novel framework for retrieval of concise entailing legal article set, Information Processing & Management (2024). DOI: 10.1016/j.ipm.2024.103949

Provided by Japan Advanced Institute of Science and Technology Citation: Retrieve-Revise-Refine: A novel framework for retrieval of concise entailing legal articles (2024, November 27) retrieved 27 November 2024 from https://techxplore.com/news/2024-11-refine-framework-concise-entailing-legal.html This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no part may be reproduced without the written permission. The content is provided for information purposes only.

Explore further

A multi-relational graph perspective on semantic similarity in program retrieval shares

Feedback to editors

Share212Tweet133ShareShare27ShareSend

Related Posts

Striking parallels between biological brains and AI during social interaction suggest fundamental principles
AI

Striking parallels between biological brains and AI during social interaction suggest fundamental principles

July 2, 2025
0

July 2, 2025 The GIST Striking parallels between biological brains and AI during social interaction suggest fundamental principles Sadie Harley scientific editor Robert Egan associate editor Editors' notes This article has been reviewed according to Science X's editorial process and policies. Editors have highlighted the following attributes while ensuring the...

Read moreDetails
Centaur: AI that thinks like us—and could help explain how we think

Centaur: AI that thinks like us—and could help explain how we think

July 2, 2025
AI might now be as good as humans at detecting emotion, political leaning and sarcasm in online conversations

AI might now be as good as humans at detecting emotion, political leaning and sarcasm in online conversations

July 2, 2025
As companies embrace AI, these leaders offer tips to make it better

As companies embrace AI, these leaders offer tips to make it better

July 2, 2025
Miami firm partners with JPMorgan Chase to bring AI-powered strategic consulting to small businesses

Miami firm partners with JPMorgan Chase to bring AI-powered strategic consulting to small businesses

July 2, 2025
Apple weighs using Anthropic or OpenAI to power Siri in major reversal

Apple weighs using Anthropic or OpenAI to power Siri in major reversal

July 2, 2025
How can AI be more energy efficient? Researchers look to human brain for inspiration

How can AI be more energy efficient? Researchers look to human brain for inspiration

July 2, 2025

Recent News

Trump’s ‘Big, Beautiful Bill’ is bad for American EVs, but it could have been worse

Trump’s ‘Big, Beautiful Bill’ is bad for American EVs, but it could have been worse

July 2, 2025
Striking parallels between biological brains and AI during social interaction suggest fundamental principles

Striking parallels between biological brains and AI during social interaction suggest fundamental principles

July 2, 2025
Perplexity joins Anthropic and OpenAI in offering a $200 per month subscription

Perplexity joins Anthropic and OpenAI in offering a $200 per month subscription

July 2, 2025

BONK Surges 10% as Tuttle Capital Sets July 16 as Earliest Launch Date for Its 2X Leveraged ETF

July 2, 2025

TOP News

  • Apple details new fee structures for App Store payments in the EU

    Apple details new fee structures for App Store payments in the EU

    540 shares
    Share 216 Tweet 135
  • Top 5 Tokenized Real Estate Platforms Transforming Property Investment

    536 shares
    Share 214 Tweet 134
  • Buying Art from a Gallery. A Guide to Making the Right Choice

    534 shares
    Share 214 Tweet 134
  • New Pokémon Legends: Z-A trailer reveals a completely large model of Lumiose Metropolis

    564 shares
    Share 226 Tweet 141
  • Bitcoin Bullishness For Q3 Grows: What Happens In Every Post-Halving Year?

    534 shares
    Share 214 Tweet 134
  • About Us
  • Contact Us
  • Privacy Policy
  • Terms of Use
Advertising: digestmediaholding@gmail.com

Disclaimer: Information found on cryptoreportclub.com is those of writers quoted. It does not represent the opinions of cryptoreportclub.com on whether to sell, buy or hold any investments. You are advised to conduct your own research before making any investment decisions. Use provided information at your own risk.
cryptoreportclub.com covers fintech, blockchain and Bitcoin bringing you the latest crypto news and analyses on the future of money.

© 2023-2025 Cryptoreportclub. All Rights Reserved

Welcome Back!

Login to your account below

Forgotten Password?

Retrieve your password

Please enter your username or email address to reset your password.

Log In
No Result
View All Result
  • Crypto news
  • AI
  • Technologies

Disclaimer: Information found on cryptoreportclub.com is those of writers quoted. It does not represent the opinions of cryptoreportclub.com on whether to sell, buy or hold any investments. You are advised to conduct your own research before making any investment decisions. Use provided information at your own risk.
cryptoreportclub.com covers fintech, blockchain and Bitcoin bringing you the latest crypto news and analyses on the future of money.

© 2023-2025 Cryptoreportclub. All Rights Reserved