KamerRaad: Enhancing Information Retrieval in Belgian National Politics through Hierarchical Summarization and Conversational Interfaces

TL;DR

KamerRaad is an AI-powered tool that uses hierarchical summarization and conversational interfaces to improve citizen engagement with Belgian parliamentary information, making political data more accessible and understandable.

Contribution

This paper introduces KamerRaad, a novel AI system combining hierarchical summarization and conversational AI to facilitate interactive political information retrieval in Belgium.

Findings

Effective extraction of key parliamentary excerpts

Enhanced user engagement through conversational interface

Potential for improved source relevance and summarization quality

Abstract

KamerRaad is an AI tool that leverages large language models to help citizens interactively engage with Belgian political information. The tool extracts and concisely summarizes key excerpts from parliamentary proceedings, followed by the potential for interaction based on generative AI that allows users to steadily build up their understanding. KamerRaad's front-end, built with Streamlit, facilitates easy interaction, while the back-end employs open-source models for text embedding and generation to ensure accurate and relevant responses. By collecting feedback, we intend to enhance the relevancy of our source retrieval and the quality of our summarization, thereby enriching the user experience with a focus on source-driven dialogue.