Decision and Gender Biases in Large Language Models: A Behavioral Economic Perspective

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Corazzini, Luca, Deriu, Elisa, Guerzoni, Marco
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915620674600960
author Corazzini, Luca
Deriu, Elisa
Guerzoni, Marco
author_facet Corazzini, Luca
Deriu, Elisa
Guerzoni, Marco
contents Large language models (LLMs) increasingly mediate economic and organisational processes, from automated customer support and recruitment to investment advice and policy analysis. These systems are often assumed to embody rational decision making free from human error; yet they are trained on human language corpora that may embed cognitive and social biases. This study investigates whether advanced LLMs behave as rational agents or whether they reproduce human behavioural tendencies when faced with classic decision problems. Using two canonical experiments in behavioural economics, the ultimatum game and a gambling game, we elicit decisions from two state of the art models, Google Gemma7B and Qwen, under neutral and gender conditioned prompts. We estimate parameters of inequity aversion and loss-aversion and compare them with human benchmarks. The models display attenuated but persistent deviations from rationality, including moderate fairness concerns, mild loss aversion, and subtle gender conditioned differences.
format Preprint
id arxiv_https___arxiv_org_abs_2511_12319
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Decision and Gender Biases in Large Language Models: A Behavioral Economic Perspective
Corazzini, Luca
Deriu, Elisa
Guerzoni, Marco
General Economics
Economics
Artificial Intelligence
I.2
Large language models (LLMs) increasingly mediate economic and organisational processes, from automated customer support and recruitment to investment advice and policy analysis. These systems are often assumed to embody rational decision making free from human error; yet they are trained on human language corpora that may embed cognitive and social biases. This study investigates whether advanced LLMs behave as rational agents or whether they reproduce human behavioural tendencies when faced with classic decision problems. Using two canonical experiments in behavioural economics, the ultimatum game and a gambling game, we elicit decisions from two state of the art models, Google Gemma7B and Qwen, under neutral and gender conditioned prompts. We estimate parameters of inequity aversion and loss-aversion and compare them with human benchmarks. The models display attenuated but persistent deviations from rationality, including moderate fairness concerns, mild loss aversion, and subtle gender conditioned differences.
title Decision and Gender Biases in Large Language Models: A Behavioral Economic Perspective
topic General Economics
Economics
Artificial Intelligence
I.2
url https://arxiv.org/abs/2511.12319