Can large language model agents simulate human trust behaviors?
Large Language Model (LLM) agents have been increasingly adopted as simulation tools to model humans in applications such as social science. However, one fundamental question remains: can LLM agents really simulate human behaviors? In this paper, we focus on one of the most critical behaviors in hum...
| المؤلفون الرئيسيون: | , , , , , , , , , |
|---|---|
| التنسيق: | Conference item |
| اللغة: | English |
| منشور في: |
Neural Information Processing Systems Foundation
2024
|
| _version_ | 1826316933338759168 |
|---|---|
| author | Xie, C Chen, C Jia, F Ye, Z Shu, K Bibi, A Hu, Z Torr, P Ghanem, B Li, G |
| author_facet | Xie, C Chen, C Jia, F Ye, Z Shu, K Bibi, A Hu, Z Torr, P Ghanem, B Li, G |
| author_sort | Xie, C |
| collection | OXFORD |
| description | Large Language Model (LLM) agents have been
increasingly adopted as simulation tools to model
humans in applications such as social science.
However, one fundamental question remains: can
LLM agents really simulate human behaviors? In
this paper, we focus on one of the most critical
behaviors in human interactions, trust, and aim to
investigate whether or not LLM agents can simulate human trust behaviors. We first find that
LLM agents generally exhibit trust behaviors, referred to as agent trust, under the framework of
Trust Games, which are widely recognized in behavioral economics. Then, we discover that LLM
agents can have high behavioral alignment with
humans regarding trust behaviors, particularly for
GPT-4, indicating the feasibility to simulate human trust behaviors with LLM agents. In addition,
we probe into the biases in agent trust and the
differences in agent trust towards agents and humans. We also explore the intrinsic properties of
agent trust under conditions including advanced
reasoning strategies and external manipulations.
We further offer important implications of our
discoveries for various scenarios where trust is
paramount. Our study provides new insights into
the behaviors of LLM agents and the fundamental
analogy between LLMs and humans. |
| first_indexed | 2024-09-25T04:09:33Z |
| format | Conference item |
| id | oxford-uuid:d3f02bef-9dfc-45a3-8c38-253c6af8fc1d |
| institution | University of Oxford |
| language | English |
| last_indexed | 2025-02-19T04:30:39Z |
| publishDate | 2024 |
| publisher | Neural Information Processing Systems Foundation |
| record_format | dspace |
| spelling | oxford-uuid:d3f02bef-9dfc-45a3-8c38-253c6af8fc1d2024-12-19T10:36:01ZCan large language model agents simulate human trust behaviors?Conference itemhttp://purl.org/coar/resource_type/c_5794uuid:d3f02bef-9dfc-45a3-8c38-253c6af8fc1dEnglishSymplectic Elements Neural Information Processing Systems Foundation2024Xie, CChen, CJia, FYe, ZShu, KBibi, AHu, ZTorr, PGhanem, BLi, GLarge Language Model (LLM) agents have been increasingly adopted as simulation tools to model humans in applications such as social science. However, one fundamental question remains: can LLM agents really simulate human behaviors? In this paper, we focus on one of the most critical behaviors in human interactions, trust, and aim to investigate whether or not LLM agents can simulate human trust behaviors. We first find that LLM agents generally exhibit trust behaviors, referred to as agent trust, under the framework of Trust Games, which are widely recognized in behavioral economics. Then, we discover that LLM agents can have high behavioral alignment with humans regarding trust behaviors, particularly for GPT-4, indicating the feasibility to simulate human trust behaviors with LLM agents. In addition, we probe into the biases in agent trust and the differences in agent trust towards agents and humans. We also explore the intrinsic properties of agent trust under conditions including advanced reasoning strategies and external manipulations. We further offer important implications of our discoveries for various scenarios where trust is paramount. Our study provides new insights into the behaviors of LLM agents and the fundamental analogy between LLMs and humans. |
| spellingShingle | Xie, C Chen, C Jia, F Ye, Z Shu, K Bibi, A Hu, Z Torr, P Ghanem, B Li, G Can large language model agents simulate human trust behaviors? |
| title | Can large language model agents simulate human trust behaviors? |
| title_full | Can large language model agents simulate human trust behaviors? |
| title_fullStr | Can large language model agents simulate human trust behaviors? |
| title_full_unstemmed | Can large language model agents simulate human trust behaviors? |
| title_short | Can large language model agents simulate human trust behaviors? |
| title_sort | can large language model agents simulate human trust behaviors |
| work_keys_str_mv | AT xiec canlargelanguagemodelagentssimulatehumantrustbehaviors AT chenc canlargelanguagemodelagentssimulatehumantrustbehaviors AT jiaf canlargelanguagemodelagentssimulatehumantrustbehaviors AT yez canlargelanguagemodelagentssimulatehumantrustbehaviors AT shuk canlargelanguagemodelagentssimulatehumantrustbehaviors AT bibia canlargelanguagemodelagentssimulatehumantrustbehaviors AT huz canlargelanguagemodelagentssimulatehumantrustbehaviors AT torrp canlargelanguagemodelagentssimulatehumantrustbehaviors AT ghanemb canlargelanguagemodelagentssimulatehumantrustbehaviors AT lig canlargelanguagemodelagentssimulatehumantrustbehaviors |