Beyond Demographics: Aligning Role-playing LLM-based Agents Using Human Belief Networks

Yun-Shiuan Chuang, Krirk Nirunwiroj, Zach Studdiford, Agam Goyal, Vincent Frigo, Sijia Yang, Dhavan Shah, Junjie Hu, Timothy Rogers


Abstract
Creating human-like large language model (LLM) agents is crucial for faithful social simulation. Having LLMs role-play based on demographic information sometimes improves human likeness but often does not. This study assessed whether LLM alignment with human behavior can be improved by integrating information from empirically-derived human belief networks. Using data from a human survey, we estimated a belief network encompassing 64 topics loading on nine non-overlapping latent factors. We then seeded LLM-based agents with an opinion on one topic, and assessed the alignment of its expressed opinions on remaining test topics with corresponding human data. Role-playing based on demographic information alone did not align LLM and human opinions, but seeding the agent with a single belief greatly improved alignment for topics related in the belief network, and not for topics outside the network. These results suggest a novel path for human-LLM belief alignment in work seeking to simulate and understand patterns of belief distributions in society.
Anthology ID:
2024.findings-emnlp.819
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2024
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
14010–14026
Language:
URL:
https://aclanthology.org/2024.findings-emnlp.819
DOI:
Bibkey:
Cite (ACL):
Yun-Shiuan Chuang, Krirk Nirunwiroj, Zach Studdiford, Agam Goyal, Vincent Frigo, Sijia Yang, Dhavan Shah, Junjie Hu, and Timothy Rogers. 2024. Beyond Demographics: Aligning Role-playing LLM-based Agents Using Human Belief Networks. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 14010–14026, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Beyond Demographics: Aligning Role-playing LLM-based Agents Using Human Belief Networks (Chuang et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-emnlp.819.pdf