JICL publication: A generative AI-based legal advice tool for small businesses in distress

Published · Updated · Thomas Wood

We are pleased to announce the publication of our paper A generative AI-based legal advice tool for small businesses in distress, in collaboration with an interdisciplinary team based in the UK and Hungary.

This paper describes the development and evaluation of the Insolvency Bot, a legal chatbot designed to provide reliable advice on corporate insolvency in England and Wales for small business owners.

We used Retrieval Augmented Generation (RAG) to enhance large language models with a curated knowledge base of 6,000 legal texts, including statutes, HMRC forms, and case law.

Thomas Wood, the director of Fast Data Science, was responsible for building the system in Python and implementing the machine learning models and vector embeddings that allow the bot to retrieve relevant legal information. Fast Data Science hosts the live version of the tool on our website at https://fastdatascience.com/insolvency

Abstract of the paper

We developed and tested the performance of a retrieval augmented generation (RAG) system for answering legal queries related to corporate insolvency in England and Wales. The Insolvency Bot relies on open-source legal information and HMRC forms to provide sound responses to a user’s query focusing on insolvency matters regulated by English law. We evaluated our bot head-to-head on an unseen test set against the unmodified versions of large language models (LLMs) gpt-3.5-turbo, gpt-4, or gpt-4o with a mark scheme similar to those used in examinations in law schools. The Insolvency Bot outperformed each unmodified LLM (p = 0.05%). An additional user experience survey suggested the need for creating two versions of the bot, one for lay people who expect practical and actionable advice and another for professionals with the relevant legal authorities. Our legal chatbot demonstrates the benefits of combining a generative AI system with a trusted knowledge base and shows future promise to cover cross-jurisdictional and insolvency-related queries and could be further improved in its technical architecture.

Citation

More information: https://pure.royalholloway.ac.uk/en/publications/a-generative-ai-based-legal-advice-tool-for-small-businesses-in-d/

Unlock Your Future in NLP!

Dive into the world of Natural Language Processing! Explore cutting-edge NLP roles that match your skills and passions.

Explore NLP Jobs

Clinical Trial Data Lookup plugin
Ai in pharmaAi in research

Clinical Trial Data Lookup plugin

Fast Data Science are pleased to announce the release Clinical Trial Data Lookup plugin for Google Sheets. It lets you look up data for multiple clinical trials by NCT ID and fills out information such as condition, sponsor, endpoints, or protocol URL in different columns.

Predicting product returns with AI
Data science consultingAi for business

Predicting product returns with AI

Why are product returns a problem? Large businesses like Amazon can swallow the cost of product returns, and generally account for it, but if you’re running a small business a single return can be very expensive. However, product returns can be a major problem for small and large businesses and it is helpful to identify when this is likely to occur.

Clinical Trial Risk Tool approved for UK government use
Ai in pharma

Clinical Trial Risk Tool approved for UK government use

Fast Data Science Ltd’s flagship AI platform, the Clinical Trial Risk Tool, has been accepted as a supplier on the UK Government’s G-Cloud 15 framework.

What we can do for you

Transform Unstructured Data into Actionable Insights

Contact us