Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2402.18180 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910852311941120 |
|---|---|
| author | Xie, Qiuejie Feng, Qiming Zhang, Tianqi Li, Qingqiu Yang, Linyi Zhang, Yuejie Feng, Rui He, Liang Gao, Shang Zhang, Yue |
| author_facet | Xie, Qiuejie Feng, Qiming Zhang, Tianqi Li, Qingqiu Yang, Linyi Zhang, Yuejie Feng, Rui He, Liang Gao, Shang Zhang, Yue |
| contents | Large language models (LLMs) are recognized as systems that closely mimic aspects of human intelligence. This capability has attracted attention from 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 framework for large language models 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. Our work is a preliminary exploration which offers great potential in practical applications. All the code and datasets will be released, with the hope of inspiring further investigations. Our code and dataset are available at: https://github.com/hasakiXie123/Human-Simulacra. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_18180 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Human Simulacra: Benchmarking the Personification of Large Language Models Xie, Qiuejie Feng, Qiming Zhang, Tianqi Li, Qingqiu Yang, Linyi Zhang, Yuejie Feng, Rui He, Liang Gao, Shang Zhang, Yue Computers and Society Large language models (LLMs) are recognized as systems that closely mimic aspects of human intelligence. This capability has attracted attention from 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 framework for large language models 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. Our work is a preliminary exploration which offers great potential in practical applications. All the code and datasets will be released, with the hope of inspiring further investigations. Our code and dataset are available at: https://github.com/hasakiXie123/Human-Simulacra. |
| title | Human Simulacra: Benchmarking the Personification of Large Language Models |
| topic | Computers and Society |
| url | https://arxiv.org/abs/2402.18180 |