Search papers, labs, and topics across Lattice.
This paper introduces PG-RAG, a retrieval-augmented generation framework that incorporates political knowledge graphs (KGs) into LLMs to improve MP ideology prediction. The framework queries a KG to capture inter-MP relationships and other relevant entities, integrating this graph-structured information into the LLM's context. Experiments on a Swiss parliamentary dataset demonstrate that PG-RAG outperforms state-of-the-art baselines by leveraging domain-specific relational information.
Political ideology prediction gets a boost: injecting LLMs with knowledge graphs of MP relationships significantly improves accuracy.
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.
ETH