Fast Data Science at The 4th Annual Conference on the Intersection of Corporate Law and Technology on 23 June 2025

We presented the Insolvency Bot at the 4th Annual Conference on the Intersection of Corporate Law and Technology at Nottingham Trent University

Dr Eugenio Vaccari of Royal Holloway University and Thomas Wood of Fast Data Science presented “A Generative AI-Based Legal Advice Tool for Small Businesses in Distress” at the 4th Annual Conference on the Intersection of Corporate Law and Technology at Nottingham Trent University

Talk abstract:

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. According to a tailor-made mark scheme, we show that our Insolvency Bot consistently outperforms LLMs queried without our RAG setup, and we show that newer versions of LLMs consistently outperform older ones when queried with the Insolvency Bot’s RAG enhancements, and its data sources. 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 potential to ensure “access to justice” to affected business owners by combining a generative AI system with a trusted knowledge base. The system could be expanded to cover cross-jurisdictional and insolvency-related queries and could be further improved in its technical architecture.

Timing of the event

The content of the event

Dr Akshaya Kamalnath delivered an interesting keynote about corporate AI, and digital governance. She discussed the implications of self-driving corporations, i.e. corporations where the board is entirely AI driven, and whether that is desirable. She brought up the idea of human in the loop and how it cannot always act as a reliable check on AI behaviour, citing research from military contexts.

Feedback which we received at the event

We had a number of fascinating queries about the Insolvency Bot. For example,

• could we extend the Insolvency Bot to query company information from Companies House via their publicly available API to improve the information content - and can we set up a collaboration with the Insolvency Service or Companies House?
• do we envisage users using this instead of getting proper legal advice?

More information: https://www.ntu.ac.uk/about-us/events/events/2025/6/the-4th-annual-conference-on-the-intersection-of-corporate-law-and-technology