October 13, 2025Open Access

Evaluating and Aligning Human Economic Risk Preferences in LLMs

View Full Paper

Ask AI

Bookmark

LLMs show reasonable decisions in personalized risk contexts, but performance declines with complexity.
Results demonstrate varying levels of risk aversion and risk-seeking behavior in LLM responses.
The proposed alignment method enhances adherence to risk preferences, addressing economic rationality issues.
Implications suggest improved AI decision-making through better alignment with human preferences in risk contexts.

Discussion

No takes yet. Share an insight, caveat, or question.

Analysis reveals LLMs' risk preferences across personas, indicating potential alignment with human economic rationality.

Liu et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark