Inducing State Anxiety in LLM Agents Reproduces Human-Like Biases in Consumer Decision-Making

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Ben-Zion, Ziv, Elyoseph, Zohar, Spiller, Tobias, Lazebnik, Teddy
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866911196910714880
author Ben-Zion, Ziv
Elyoseph, Zohar
Spiller, Tobias
Lazebnik, Teddy
author_facet Ben-Zion, Ziv
Elyoseph, Zohar
Spiller, Tobias
Lazebnik, Teddy
contents Large language models (LLMs) are rapidly evolving from text generators to autonomous agents, raising urgent questions about their reliability in real-world contexts. Stress and anxiety are well known to bias human decision-making, particularly in consumer choices. Here, we tested whether LLM agents exhibit analogous vulnerabilities. Three advanced models (ChatGPT-5, Gemini 2.5, Claude 3.5-Sonnet) performed a grocery shopping task under budget constraints (24, 54, 108 USD), before and after exposure to anxiety-inducing traumatic narratives. Across 2,250 runs, traumatic prompts consistently reduced the nutritional quality of shopping baskets (Change in Basket Health Scores of -0.081 to -0.126; all pFDR<0.001; Cohens d=-1.07 to -2.05), robust across models and budgets. These results show that psychological context can systematically alter not only what LLMs generate but also the actions they perform. By reproducing human-like emotional biases in consumer behavior, LLM agents reveal a new class of vulnerabilities with implications for digital health, consumer safety, and ethical AI deployment.
format Preprint
id arxiv_https___arxiv_org_abs_2510_06222
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Inducing State Anxiety in LLM Agents Reproduces Human-Like Biases in Consumer Decision-Making
Ben-Zion, Ziv
Elyoseph, Zohar
Spiller, Tobias
Lazebnik, Teddy
Human-Computer Interaction
General Economics
Economics
Large language models (LLMs) are rapidly evolving from text generators to autonomous agents, raising urgent questions about their reliability in real-world contexts. Stress and anxiety are well known to bias human decision-making, particularly in consumer choices. Here, we tested whether LLM agents exhibit analogous vulnerabilities. Three advanced models (ChatGPT-5, Gemini 2.5, Claude 3.5-Sonnet) performed a grocery shopping task under budget constraints (24, 54, 108 USD), before and after exposure to anxiety-inducing traumatic narratives. Across 2,250 runs, traumatic prompts consistently reduced the nutritional quality of shopping baskets (Change in Basket Health Scores of -0.081 to -0.126; all pFDR<0.001; Cohens d=-1.07 to -2.05), robust across models and budgets. These results show that psychological context can systematically alter not only what LLMs generate but also the actions they perform. By reproducing human-like emotional biases in consumer behavior, LLM agents reveal a new class of vulnerabilities with implications for digital health, consumer safety, and ethical AI deployment.
title Inducing State Anxiety in LLM Agents Reproduces Human-Like Biases in Consumer Decision-Making
topic Human-Computer Interaction
General Economics
Economics
url https://arxiv.org/abs/2510.06222