Consult is a machine learning and LLM-powered tool to automate the processing of public consultations.

Consultations cost Government around £80m a year Public consultations are a critical part of the process of making laws, but analysing consultation responses is complex and very time consuming. The government runs 700-800 consultations a year on matters of importance to the public. Some are very small, but a large consultation might attract hundreds of thousands of written responses.

A consultation attracting 30,000 responses requires a team of around 25 analysts for 3 months to analyse the data and write the report. And it’s not unheard of to get double that number. If we can apply automation in a way that is fair, effective and accountable, and surround this with good software that puts the policy analyst and decision maker at the center, we could save most of that time and money, and develop more informed policies.

Working with the No10 data science team (10DS), the Incubator for Artificial Intelligence (i.AI) is developing a tool to make the process of analysing public responses to government consultations faster and fairer.

The Consult tool uses AI and data science techniques to automatically extract patterns and themes from the responses, and turns them into dashboards for policy makers.

The goal is for computers to do what they are best at: finding patterns and analysing large amounts of data. That means humans are free to do the work of understanding those patterns.

How Consult works i.AI has developed a brand new technique for topic modelling using Large Language Models (LLMs), that takes a two step approach:

Identify the themes in a set of responses that are descriptive, context aware and relevant to human analysts Map those themes back onto the responses By breaking down the process into these two steps, we give the human analysts full control over the process. The outputs here give the analysts key insights into the views of the public.