REVIEW 6 cited by
GPT in Game Theory Experiments
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
This paper explores the use of Generative Pre-trained Transformers (GPT) in strategic game experiments, specifically the ultimatum game and the prisoner's dilemma. I designed prompts and architectures to enable GPT to understand the game rules and to generate both its choices and the reasoning behind decisions. The key findings show that GPT exhibits behaviours similar to human responses, such as making positive offers and rejecting unfair ones in the ultimatum game, along with conditional cooperation in the prisoner's dilemma. The study explores how prompting GPT with traits of fairness concern or selfishness influences its decisions. Notably, the "fair" GPT in the ultimatum game tends to make higher offers and reject offers more frequently compared to the "selfish" GPT. In the prisoner's dilemma, high cooperation rates are maintained only when both GPT players are "fair". The reasoning statements GPT produces during gameplay reveal the underlying logic of certain intriguing patterns observed in the games. Overall, this research shows the potential of GPT as a valuable tool in social science research, especially in experimental studies and social simulations.
Forward citations
Cited by 6 Pith papers
-
A game theory for foundation models shows new paths to rational cooperation through similarity inference
Foundation-model agents that plan by predicting both the world and themselves can rationally cooperate in one-shot social dilemmas by inferring behavioral similarity from interaction history.
-
Do Humans Bargain Differently with AI? Evidence from Alternating-Offer Games
Humans make lower opening offers to AI than to humans in an alternating-offer bargaining game, and accept more unfair AI offers when the AI's payoff feeds into their own payment.
-
From Digital Distrust to Codified Honesty: Experimental Evidence on Generative AI in Credence Goods Markets
LLM experts in credence goods markets reduce efficiency and consumer surplus unless liability or transparent prosocial objectives operate, and expert delegation with transparent objectives can outperform human-only markets.
-
The Effect of State Representation on LLM Agent Behavior in Dynamic Routing Games
In a repeated Braess routing game, LLM agents given summarized, regret-based, and own-action-only state representations converge closer to Nash equilibrium and behave more stably than agents given full chat transcript...
-
When Ethics and Payoffs Diverge: LLM Agents in Morally Charged Social Dilemmas
Across morally framed prisoner's dilemmas and public goods games, none of nine LLMs consistently chooses the ethical action when it conflicts with payoff, with cooperation rates from 7.9% to 76.3%.
-
Game Theory Meets Large Language Models: A Systematic Survey with Taxonomy and New Frontiers
A taxonomy-based survey of bidirectional game theory and LLM research, spanning evaluation, alignment, economic competition, and LLM-driven game solving.
Discussion (0). Continue with ORCID to comment.