Salvato in:
Dettagli Bibliografici
Autori principali: Shen, Chenglei, Xie, Guofu, Zhang, Xiao, Xu, Jun
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2402.18807
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866929259204837376
author Shen, Chenglei
Xie, Guofu
Zhang, Xiao
Xu, Jun
author_facet Shen, Chenglei
Xie, Guofu
Zhang, Xiao
Xu, Jun
contents Large language models (LLMs) are now increasingly utilized for role-playing tasks, especially in impersonating domain-specific experts, primarily through role-playing prompts. When interacting in real-world scenarios, the decision-making abilities of a role significantly shape its behavioral patterns. In this paper, we concentrate on evaluating the decision-making abilities of LLMs post role-playing thereby validating the efficacy of role-playing. Our goal is to provide metrics and guidance for enhancing the decision-making abilities of LLMs in role-playing tasks. Specifically, we first use LLMs to generate virtual role descriptions corresponding to the 16 personality types of Myers-Briggs Type Indicator (abbreviated as MBTI) representing a segmentation of the population. Then we design specific quantitative operations to evaluate the decision-making abilities of LLMs post role-playing from four aspects: adaptability, exploration$\&$exploitation trade-off ability, reasoning ability, and safety. Finally, we analyze the association between the performance of decision-making and the corresponding MBTI types through GPT-4. Extensive experiments demonstrate stable differences in the four aspects of decision-making abilities across distinct roles, signifying a robust correlation between decision-making abilities and the roles emulated by LLMs. These results underscore that LLMs can effectively impersonate varied roles while embodying their genuine sociological characteristics.
format Preprint
id arxiv_https___arxiv_org_abs_2402_18807
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle On the Decision-Making Abilities in Role-Playing using Large Language Models
Shen, Chenglei
Xie, Guofu
Zhang, Xiao
Xu, Jun
Computation and Language
Artificial Intelligence
Large language models (LLMs) are now increasingly utilized for role-playing tasks, especially in impersonating domain-specific experts, primarily through role-playing prompts. When interacting in real-world scenarios, the decision-making abilities of a role significantly shape its behavioral patterns. In this paper, we concentrate on evaluating the decision-making abilities of LLMs post role-playing thereby validating the efficacy of role-playing. Our goal is to provide metrics and guidance for enhancing the decision-making abilities of LLMs in role-playing tasks. Specifically, we first use LLMs to generate virtual role descriptions corresponding to the 16 personality types of Myers-Briggs Type Indicator (abbreviated as MBTI) representing a segmentation of the population. Then we design specific quantitative operations to evaluate the decision-making abilities of LLMs post role-playing from four aspects: adaptability, exploration$\&$exploitation trade-off ability, reasoning ability, and safety. Finally, we analyze the association between the performance of decision-making and the corresponding MBTI types through GPT-4. Extensive experiments demonstrate stable differences in the four aspects of decision-making abilities across distinct roles, signifying a robust correlation between decision-making abilities and the roles emulated by LLMs. These results underscore that LLMs can effectively impersonate varied roles while embodying their genuine sociological characteristics.
title On the Decision-Making Abilities in Role-Playing using Large Language Models
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2402.18807