A semantic embedding space based on large language models for modelling human beliefs

TL;DR

This paper introduces a neural embedding space derived from large language models to analyze and predict human beliefs and their interrelations across social issues, using online debate data.

Contribution

It presents a novel method to map thousands of beliefs into a neural space, capturing their interconnectedness and polarization, advancing understanding of belief dynamics.

Findings

Positions in the belief space predict new beliefs.

Belief space distances estimate cognitive dissonance.

The model reveals interconnectedness of diverse beliefs.

Abstract

Beliefs form the foundation of human cognition and decision-making, guiding our actions and social connections. A model encapsulating beliefs and their interrelationships is crucial for understanding their influence on our actions. However, research on belief interplay has often been limited to beliefs related to specific issues and relied heavily on surveys. We propose a method to study the nuanced interplay between thousands of beliefs by leveraging an online user debate data and mapping beliefs onto a neural embedding space constructed using a fine-tuned large language model (LLM). This belief space captures the interconnectedness and polarization of diverse beliefs across social issues. Our findings show that positions within this belief space predict new beliefs of individuals and estimate cognitive dissonance based on the distance between existing and new beliefs. This study demonstrates how LLMs, combined with collective online records of human beliefs, can offer insights into the fundamental principles that govern human belief formation.