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/

Your NLP Career Awaits!

Ready to take the next step in your NLP journey? Connect with top employers seeking talent in natural language processing. Discover your dream job!

Find Your Dream Job

Fast Data Science appointed as official supplier on AI Framework
Data science consulting

Fast Data Science appointed as official supplier on AI Framework

Fast Data Science Ltd has officially been accepted onto the Artificial Intelligence DPS (Dynamic Purchasing System) framework as an Appointed Supplier. This status validates our ongoing commitment to delivering cutting-edge AI, machine learning, and data science solutions, while making our services directly accessible to contracting authorities across the UK public sector.

Fast Data Science available for UK government procurement
Ai for business

Fast Data Science available for UK government procurement

Fast Data Science is listed on the UK Government’s Digital Marketplace under the G-Cloud 15 Framework and Digital Outcomes 6 as well as the Artificial Intelligence DPS.

Harmony Meta at DRIVE-Health on 24 September 2026
Ai in researchEvents

Harmony Meta at DRIVE-Health on 24 September 2026

Thomas Wood, director of Fast Data Science, and Dr Bettina Moltrecht of UCL will be appearing at DRIVE-Health, an event hosted at Kings College London, to present Harmony Meta on 24 September 2026.

What we can do for you

Transform Unstructured Data into Actionable Insights

Contact us