🧪 Test?View on arXiv
Prospect Theory in Large Language Models: A Meta-Analysis of Loss Aversion, Diminishing Sensitivity, and Probability Weighting
Not provided
probability weightingloss aversionlanguage models
2610.33103
Builder Relevance
1h ago60%
Abstract
This paper examines whether Large Language Models (LLMs) exhibit properties of prospect theory, revealing modest loss aversion and diminishing sensitivity, but retaining human-like probability distortion.
Reality Card
Core Claim
LLMs show little loss aversion and diminishing sensitivity compared to humans, but exhibit human-like probability distortion.
Method / Result
Pooled loss aversion $BB$ is 1.26, significantly lower than the strongest human estimate of 1.96.
Limitations
The findings may vary significantly based on specific model families and fitting methods.
Paper to code
Verified implementation resources so builders can test the paper’s claims instead of stopping at the abstract.
No verified implementation link has been attached yet. AIBuzzHub will keep this panel separate from unverified search results.