Do generative AI models, particularly large language models (LLMs), exhibit systematic behavioral biases in economic and financial decisions? If so, how can these biases be mitigated? Drawing on the cognitive psychology and experimental economics literatures, we conduct the most comprehensive set of experiments to date—originally designed to document human biases—on prominent LLM families across model versions and scales. We document systematic patterns in LLM behavior. In preference-based tasks, responses become more human-like as models become more advanced or larger, while in belief-based tasks, advanced large-scale models frequently generate rational responses. Prompting LLMs to make rational decisions reduces biases.

We propose a framework for rigorous inference in the evaluation of asset pricing anomalies that explicitly accounts for multiple methodological choices. We demonstrate that running multiple paths on the same dataset results in high correlation across outcomes, distorting inference. Alternatively, path-specific resampling reduces outcome correlations and tightens the confidence interval of the average return. Accounting for across- and within-path variability allows us to decompose the variance of the average return into a standard error, a nonstandard error, and a correlation term. We define the nonstandard Sharpe ratio as the ratio of the average return to the nonstandard error and show that this metric enables the identification of persistent anomalies. Empirically, we show that nonstandard errors dominate standard errors, and that 24\% of the anomalies in our sample (26 out of 107) are fully persistent.

We challenge the restrictive "one-size-fits-all'' assumption of standard asset pricing models by demonstrating that the stochastic discount factor is locally sparse within economic clusters but globally dense in the aggregate. Using a Lasso Fama-MacBeth Clustering Model, we identify "uncommon factors'' -- risks that command premia only within specific asset clusters or economic regimes. In the cross section, one-month momentum and unexpected earnings are the most pervasive priced components, while other signals are concentrated in specific segments. Across NBER business cycles, the active factor set itself rotates: recession-period premia span a broad set of signals, whereas expansions are more concentrated. This heterogeneity generates substantial economic value: cluster-based value-weighted portfolios deliver out-of-sample annualized Sharpe ratios up to 2 and monthly alphas above 1.7% unspanned by standard factor models. Our results suggest that apparent instability in characteristic premia is partly consistent with market segmentation, with some characteristics priced only within specific asset segments.