The Machine Psychology of Cooperation: Can GPT models operationalise prompts for altruism, cooperation, competitiveness and selfishness in economic games?

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Phelps, Steve, Russell, Yvan I.
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910506898423808
author Phelps, Steve
Russell, Yvan I.
author_facet Phelps, Steve
Russell, Yvan I.
contents We investigated the capability of the GPT-3.5 large language model (LLM) to operationalize natural language descriptions of cooperative, competitive, altruistic, and self-interested behavior in two social dilemmas: the repeated Prisoners Dilemma and the one-shot Dictator Game. Using a within-subject experimental design, we used a prompt to describe the task environment using a similar protocol to that used in experimental psychology studies with human subjects. We tested our research question by manipulating the part of our prompt which was used to create a simulated persona with different cooperative and competitive stances. We then assessed the resulting simulacras' level of cooperation in each social dilemma, taking into account the effect of different partner conditions for the repeated game. Our results provide evidence that LLMs can, to some extent, translate natural language descriptions of different cooperative stances into corresponding descriptions of appropriate task behaviour, particularly in the one-shot game. There is some evidence of behaviour resembling conditional reciprocity for the cooperative simulacra in the repeated game, and for the later version of the model there is evidence of altruistic behaviour. Our study has potential implications for using LLM chatbots in task environments that involve cooperation, e.g. using chatbots as mediators and facilitators in public-goods negotiations.
format Preprint
id arxiv_https___arxiv_org_abs_2305_07970
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle The Machine Psychology of Cooperation: Can GPT models operationalise prompts for altruism, cooperation, competitiveness and selfishness in economic games?
Phelps, Steve
Russell, Yvan I.
Computer Science and Game Theory
Artificial Intelligence
Computers and Society
General Economics
Economics
I.2.0
We investigated the capability of the GPT-3.5 large language model (LLM) to operationalize natural language descriptions of cooperative, competitive, altruistic, and self-interested behavior in two social dilemmas: the repeated Prisoners Dilemma and the one-shot Dictator Game. Using a within-subject experimental design, we used a prompt to describe the task environment using a similar protocol to that used in experimental psychology studies with human subjects. We tested our research question by manipulating the part of our prompt which was used to create a simulated persona with different cooperative and competitive stances. We then assessed the resulting simulacras' level of cooperation in each social dilemma, taking into account the effect of different partner conditions for the repeated game. Our results provide evidence that LLMs can, to some extent, translate natural language descriptions of different cooperative stances into corresponding descriptions of appropriate task behaviour, particularly in the one-shot game. There is some evidence of behaviour resembling conditional reciprocity for the cooperative simulacra in the repeated game, and for the later version of the model there is evidence of altruistic behaviour. Our study has potential implications for using LLM chatbots in task environments that involve cooperation, e.g. using chatbots as mediators and facilitators in public-goods negotiations.
title The Machine Psychology of Cooperation: Can GPT models operationalise prompts for altruism, cooperation, competitiveness and selfishness in economic games?
topic Computer Science and Game Theory
Artificial Intelligence
Computers and Society
General Economics
Economics
I.2.0
url https://arxiv.org/abs/2305.07970