LLMs can be profile-calibrated to exhibit human-like behavioral parameters including loss aversion, herding, and extrapolation, enabling agent-based models to generate momentum and reversal patterns consistent with empirical asset pricing evidence.
Experimental tests of the endowment effect and the coase theorem.Journal of Political Economy, 98(6):1325–1348, 1990
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
econ.GN 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Calibrating Behavioral Parameters with Large Language Models
LLMs can be profile-calibrated to exhibit human-like behavioral parameters including loss aversion, herding, and extrapolation, enabling agent-based models to generate momentum and reversal patterns consistent with empirical asset pricing evidence.