Search papers, labs, and topics across Lattice.
This paper investigates whether GPT-4.1 exhibits socioeconomic persona-conditioned risk behavior consistent with Prospect Theory in a simulated slot-machine environment. The model was assigned Rich, Middle-income, and Poor personas and tasked with playing slot machines with varying payout probabilities. Results show that GPT-4.1 reproduces key behavioral patterns predicted by Prospect Theory, with the Poor persona exhibiting significantly higher risk-seeking behavior than the Rich persona, suggesting that LLMs may implicitly encode cognitive economic biases.
GPT-4.1, without explicit prompting, replicates human-like risk biases from Prospect Theory when assigned different socioeconomic personas in a gambling simulation, revealing potential cognitive biases implicitly learned during pretraining.
Large language models (LLMs) are increasingly deployed as autonomous agents in uncertain, sequential decision-making contexts. Yet it remains poorly understood whether the behaviors they exhibit in such environments reflect principled cognitive patterns or simply surface-level prompt mimicry. This paper presents a controlled experiment in which GPT-4.1 was assigned one of three socioeconomic personas (Rich, Middle-income, and Poor) and placed in a structured slot-machine environment with three distinct machine configurations: Fair (50%), Biased Low (35%), and Streak (dynamic probability increasing after consecutive losses). Across 50 independent iterations per condition and 6,950 recorded decisions, we find that the model reproduces key behavioral signatures predicted by Kahneman and Tversky's Prospect Theory without being instructed to do so. The Poor persona played a mean of 37.4 rounds per session (SD=15.5) compared to 1.1 rounds for the Rich persona (SD=0.31), a difference that is highly significant (Kruskal-Wallis H=393.5, p<2.2e-16). Risk scores by persona show large effect sizes (Cohen's d=4.15 for Poor vs Rich). Emotional labels appear to function as post-hoc annotations rather than decision drivers (chi-square=3205.4, Cramer's V=0.39), and belief-updating across rounds is negligible (Spearman rho=0.032 for Poor persona, p=0.016). These findings carry implications for LLM agent design, interpretability research, and the broader question of whether classical cognitive economic biases are implicitly encoded in large-scale pretrained language models.
