The team at the Hartree Centre North East Hub worked with Lamp House Strategy to develop a model that uses artificial intelligence to standardise, optimise and improve information gathering for the law firm review process.

‍

Challenge

Lamp House Strategy is a market research and insights agency. They capture and analyse data to help large corporate law firms benchmark and develop their responsible business strategies. Reviewing literature and other evidence from each law firm they work with can take many hundreds of hours to complete. Lamp House Strategy were keen to explore how better use of data and AI could lighten the load for the team and help them be better and more consistently informed about a law firm’s activities. They were keen to leverage technology to standardise, improve and optimise the professional review process they offer, not to replace or automate the work of their highly skilled reviewers.

‍

Approach

The Hartree Centre North East Hub team worked to produce a proof-of-concept application to show how large language models (LLM) could be used to extract meaningful insights and key metrics from law companies’ online PDF reports. The team at Lamp House provided a sample dataset that had been manually scored and reviewed, with the accompanying data that had been extracted. Through the use of prompt engineering, we were to create an extraction process that reviewed documents and extracted key information, reasoning as to why this information was selected and guided the reviewer to the page within the document where add further PDF data. Benefits the information could be found. The proof-of-concept application included the ability for Lamp House Strategy to extend the work done on the project by allowing the ability to create their own prompts and to add further PDF data.

‍

‍

Benefits

Through the project Lamp House strategy have been able to explore the use of AI, and more specifically LLMs, in helping to improve their working practices when conducting review on behalf of their clients. Additionally they have now had a working prototype that allows them to add further data as they require, and to amend to the prompting to improve the operation of the tool going forward, adding the ability to extract new insights going forward.  This PoC tool will hopefully save Lamp House Strategy countless hours of work, by guiding their skilled reviewers to the pertinent information much faster than their current processes allow.

"We have been inspired by the potential of AI to transform our review process and unlock new insights for our clients."

- Hayley Fothergill, Lamp House Strategy

“The collaboration with the Hartree team has been invaluable in helping us explore the power of Large Language Models to streamline our work and enhance our client deliverables. We’re excited to continue this journey, leveraging the proof-of-concept application to drive efficiency gains and uncover fresh perspectives."

- Tom Kelsey, Lamp House Strategy

‍

Further Information

This work was completed as part of one of our collaborative data projects. The projects are up to 12 weeks in duration and give you access to a wide range of expertise across our team of data scientists and data engineers. We will work alongside your team to scope your data science or engineering project, build a prototype solution, and explore options to deploy it within your organisation. You can learn more about them on our webpage here.

If you would like to learn more about the Hartree Centre North East Hub or our collaborative data projects, please get in touch with us at: hello@hartreenortheast.uk