Insolvency Bot

Insolvency bot screenshot - AI and NLP for legal

An insolvency bot leveraging LLMs to answer questions about English insolvency law, using Retrieval Augmented Generation (RAG). You can read more in our accompanying blog post.

The information provided on this website does not, and is not intended to, constitute legal advice.

Stuck for ideas? You are a: in and your problem is:

[enter a text and click Answer and the legislation will be shown here]

User experience feedback form - we are collecting user feedback on the Insolvency Bot and any feedback is welcome!

Resources, DOIs, and citing the project

Click here to download the slideshow presented at the JURIX 2023 conference.

Our paper was published in the proceedings of the 2023 JURIX conference in Maastricht, the Netherlands. DOIDOI10.3233/FAIA23097910.3233/FAIA230979

Ribary, M., Krause, P., Orban, M., Vaccari, E., Wood, T.A., Prompt Engineering and Provision of Context in Domain Specific Use of GPT, Frontiers in Artificial Intelligence and Applications 379: Legal Knowledge and Information Systems, 2023.

You can find the long form of our paper here: DOIDOI10.5281/zenodo.1002973510.5281/zenodo.10029735

The DOI of our evaluation scripts is as follows: DOIDOI10.5281/zenodo.829210510.5281/zenodo.8292105

Insolvency Bot at the 5th Insolvency Symposium

We presented the Insolvency Bot at the 5th Insolvency Symposium, at the School of Law and Social Sciences, Royal Holloway, University of London on 25 April 2024.

Video of Thomas Wood and Marton Ribary presenting the Insolvency Bot at the Insolvency Symposium. Our presentation starts at 2h 10min 28sec.

Who worked on the Insolvency Bot AI/NLP project?

Paul Krause

Paul Krause is Emeritus Professor at the University of Surrey. He has been working on theoretical and practical aspects of AI for forty years. His career has included time at the National Physical Laboratory, the Imperial Cancer Research Fund, and Philips Research Laboratories.

Miklos Orban

Miklós Orbán is a legal entrepreneur with 20+ years of experience as a New York and Hungarian qualified lawyer. He is the CTO of gunnercooke LLP and the managing parter of gunnercooke CEE. In addition, he is the co-founder of OPL, EXPLICO and Lexitup. He graduated from ELTE Law School and Georgetown University where he was a Fulbright scholar. Miklos is a Visiting Professor in practice at the University of Surrey.

Marton Ribary

Marton Ribary is a Lecturer in Law at Royal Holloway, University of London where his research focuses on legal reasoning. He works with Natural Language Processing (NLP) and algorithmic rule modelling methods applied to historical (Roman and Rabbinic) as well as modern (English) texts in private law.

Eugenio Vaccari

Eugenio Vaccari is a Senior Lecturer in Law at the Department of Law and Criminology at Royal Holloway, University of London. Eugenio is a qualified Italian lawyer specialized in corporate insolvency and bankruptcy law. Eugenio is an active member of several leading institutions in the field, including III NextGen Class XI (where he is member of the Executive Committee), INSOL International, INSOL Europe, the Insolvency Law Academy (where he is co-chair of the Emerging Scholars Group) and the Insolvency Lawyers’ Association (UK). Eugenio is also an Academic Fellow of the Middle Temple. He co-authored English Corporate Insolvency Law: A Primer, which was an invaluable resource for the development of this project.

  • Vaccari, Eugenio, and Emilie Ghio. English Corporate Insolvency Law: A Primer. Edward Elgar Publishing, 2022.

Thomas Wood

Thomas Wood is director of AI/NLP company Fast Data Science. He holds a Masters in natural language processing (MPhil in Computer Speech, Text and Internet Technology) from the University of Cambridge. He has worked in a psychology lab in London, two small companies in Germany and Spain, and has worked in Tesco’s data science team. In 2018, he founded Fast Data Science to offer consulting services in natural language processing and machine learning, focusing on the healthcare and pharmaceutical industries. He has built machine learning models to extract important information from unstructured documents such as interview transcripts, scientific papers, clinical trial protocols, and other scientific and healthcare data.

What we can do for you

Transform Unstructured Data into Actionable Insights

Contact us