Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                

Virtual Personas for Language Models via an Anthology of Backstories

Suhong Moon, Marwa Abdulhai, Minwoo Kang, Joseph Suh, Widyadewi Soedarmadji, Eran Kohen Behar, David Chan


Abstract
Large language models (LLMs) are trained from vast repositories of text authored by millions of distinct authors, reflecting an enormous diversity of human traits. While these models bear the potential to be used as approximations of human subjects in behavioral studies, prior efforts have been limited in steering model responses to match individual human users. In this work, we introduce Anthology, a method for conditioning LLMs to particular virtual personas by harnessing open-ended life narratives, which we refer to as backstories. We show that our methodology enhances the consistency and reliability of experimental outcomes while ensuring better representation of diverse sub-populations. Across three nationally representative human surveys conducted as part of Pew Research Center’s American Trends Panel (ATP), we demonstrate that Anthology achieves up to 18% improvement in matching the response distributions of human respondents and 27% improvement in consistency metrics.
Anthology ID:
2024.emnlp-main.1110
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
19864–19897
Language:
URL:
https://aclanthology.org/2024.emnlp-main.1110/
DOI:
10.18653/v1/2024.emnlp-main.1110
Bibkey:
Cite (ACL):
Suhong Moon, Marwa Abdulhai, Minwoo Kang, Joseph Suh, Widyadewi Soedarmadji, Eran Kohen Behar, and David Chan. 2024. Virtual Personas for Language Models via an Anthology of Backstories. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 19864–19897, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Virtual Personas for Language Models via an Anthology of Backstories (Moon et al., EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-main.1110.pdf