Human Simulacra: Benchmarking the Personification of Large Language Models

Qiujie Xie, Qiming Feng, Tianqi Zhang, Qingqiu Li, Linyi Yang, Yuejie Zhang, Rui Feng, Liang He, Shang Gao, Yue Zhang

Keywords: Large Language Models, Human simulation

TL;DR: We are the first to introduce a benchmark for the personification of large language models, including high-quality data, rigorous and innovative evaluation methods, and comprehensive benchmark tests.

Abstract: Large Language Models (LLMs) are recognized as systems that closely mimic aspects of human intelligence. This capability has attracted the attention of the social science community, who see the potential in leveraging LLMs to replace human participants in experiments, thereby reducing research costs and complexity. In this paper, we introduce a benchmark for LLMs personification, including a strategy for constructing virtual characters' life stories from the ground up, a Multi-Agent Cognitive Mechanism capable of simulating human cognitive processes, and a psychology-guided evaluation method to assess human simulations from both self and observational perspectives. Experimental results demonstrate that our constructed simulacra can produce personified responses that align with their target characters. We hope this work will serve as a benchmark in the field of human simulation, paving the way for future research.

Primary Area: datasets and benchmarks

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 8815