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

arXiv: https://arxiv.org/abs/2408.07237 · HTML: https://mlsanity.com/paper/2408.07237/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 47 references that are in the map.
- First posted on arXiv 13 Aug 2024.

## Builds on (most cited first, 20 of 20)

- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Distributed Representations of Sentences and Documents](https://mlsanity.com/paper/1405.4053/) (2014)
- [Bias and Fairness in Large Language Models: A Survey](https://mlsanity.com/paper/2309.00770/) (2023)
- [Large Language Models meet Collaborative Filtering: An Efficient All-round LLM-based Recommender System](https://mlsanity.com/paper/2404.11343/) (2024)
- [Unsupervised User Stance Detection on Twitter](https://mlsanity.com/paper/1904.02000/) (2019)
- [Exploring the Role of Prior Beliefs for Argument Persuasion](https://mlsanity.com/paper/1906.11301/) (2019)
- [SemAxis: A Lightweight Framework to Characterize Domain-Specific Word Semantics Beyond Sentiment](https://mlsanity.com/paper/1806.05521/) (2018)
- [A Corpus for Modeling User and Language Effects in Argumentation on Online Debating](https://mlsanity.com/paper/1906.11310/) (2019)
- [GraphNLI: A Graph-based Natural Language Inference Model for Polarity Prediction in Online Debates](https://mlsanity.com/paper/2202.08175/) (2022)
- [Embeddings-Based Clustering for Target Specific Stances: The Case of a Polarized Turkey](https://mlsanity.com/paper/2005.09649/) (2020)
- [Origins of power-law degree distribution in the heterogeneity of human activity in social networks](https://mlsanity.com/paper/1304.4523/) (2013)
- [Collective dynamics of belief evolution under cognitive coherence and social conformity](https://mlsanity.com/paper/1509.01502/) (2015)
- [Emergence of simple and complex contagion dynamics from weighted belief networks](https://mlsanity.com/paper/2301.02368/) (2023)
- [Measuring Belief Dynamics on Twitter](https://mlsanity.com/paper/2211.11947/) (2022)
- [Using a Cognitive Network Model of Moral and Social Beliefs to Explain Belief Change](https://mlsanity.com/paper/2102.10751/) (2021)

## Built on by (most cited first, 9 of 9)

- [Bias in Large Language Models: Origin, Evaluation, and Mitigation](https://mlsanity.com/paper/2411.10915/) (2024)
- [Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP vs Rule Extraction vs RuleSHAP](https://mlsanity.com/paper/2505.11189/) (2025)
- [Debiasing International Attitudes: LLM Agents for Simulating US-China Perception Changes](https://mlsanity.com/paper/2508.08837/) (2025)
- [Big Data and the Computational Social Science of Entrepreneurship and Innovation](https://mlsanity.com/paper/2505.08706/) (2025)
- [LLM-BT-Terms: Back-Translation as a Framework for Terminology Standardization and Dynamic Semantic Embedding](https://mlsanity.com/paper/2506.08174/) (2025)
- [What Helps Language Models Predict Human Beliefs: Demographics or Prior Stances?](https://mlsanity.com/paper/2511.18616/) (2025)
- [Validating LLMs in social science: Epistemic threats and emerging norms](https://mlsanity.com/paper/2607.07915/) (2026)
- [Count Evidence, Not Sentences: Tempered Evidence Fusion of LLM Judgments for Long-Text Value Measurement](https://mlsanity.com/paper/2609.27165/) (2026)
- [Social Choice Foundations for Simulation-Augmented Generation](https://mlsanity.com/paper/2609.38287/) (2026)

## Abstract (arXiv)

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.