Political Actor Agent: Simulating Legislative System for Roll Call Votes Prediction with Large Language Models

TL;DR

This paper introduces the Political Actor Agent (PAA), an agent-based framework utilizing Large Language Models to predict legislative roll call votes with improved accuracy and interpretability, addressing limitations of existing embedding-based methods.

Contribution

The paper presents a novel agent-based approach using Large Language Models for legislative vote prediction, enhancing interpretability and reducing reliance on manual features.

Findings

PAA outperforms traditional embedding methods in prediction accuracy.

PAA provides human-understandable reasoning for legislative decisions.

Experimental validation on U.S. House voting records confirms effectiveness.

Abstract

Predicting roll call votes through modeling political actors has emerged as a focus in quantitative political science and computer science. Widely used embedding-based methods generate vectors for legislators from diverse data sets to predict legislative behaviors. However, these methods often contend with challenges such as the need for manually predefined features, reliance on extensive training data, and a lack of interpretability. Achieving more interpretable predictions under flexible conditions remains an unresolved issue. This paper introduces the Political Actor Agent (PAA), a novel agent-based framework that utilizes Large Language Models to overcome these limitations. By employing role-playing architectures and simulating legislative system, PAA provides a scalable and interpretable paradigm for predicting roll-call votes. Our approach not only enhances the accuracy of predictions but also offers multi-view, human-understandable decision reasoning, providing new insights into political actor behaviors. We conducted comprehensive experiments using voting records from the 117-118th U.S. House of Representatives, validating the superior performance and interpretability of PAA. This study not only demonstrates PAA's effectiveness but also its potential in political science research.