Graph-Augmented LLMs for Swiss MP Ideology Prediction

TL;DR

This paper introduces PG-RAG, a retrieval-augmented generation framework that enhances Swiss MP ideology prediction by integrating a political knowledge graph with LLMs, improving accuracy over existing methods.

Contribution

The work presents a novel LLM-based approach that incorporates a political knowledge graph for better parliamentary ideology prediction, capturing both textual and relational information.

Findings

Graph-augmented models outperform state-of-the-art baselines.

Incorporating relational knowledge improves prediction accuracy.

The approach highlights the value of domain-specific relational data in political modeling.

Abstract

Approximating the ideological position of Members of Parliament (MPs) is a fundamental task in political science, helping researchers understand legislative behavior, party alignment, and policy preferences. While Large Language Models (LLMs) have shown promising results in estimating MPs' ideological stances, there are more actors and elements in the parliamentary system, and relations between them, that could provide a wider and more informative picture. However, due to the complexity of integrating them in the prediction task, these additional elements are generally ignored. In this work, we propose an LLM framework, PG-RAG, that implements a retrieval-augmented generation pipeline: it first queries a political knowledge graph (KG) and then integrates the resulting graph-structured information into the context. This allows for capturing both textual semantics and inter-MP relationships, another relevant information source in any parliamentary system. We evaluate the approach on the task of ideology prediction, using data from a Swiss parliamentary dataset. When comparing graph-augmented models against several state-of-the-art baselines, the results demonstrate that incorporating this enriched information, which encodes information about different entities and relations, improves prediction performance. These results help to highlight the value of domain-specific relational information in modeling political behavior.