Persona-Aware Evaluation of Cognitive Bias in LLMs: From Benchmark to Applied Decision-Making

Abstract

We present a persona-aware evaluation suite that couples a 12-category cognitive-bias benchmark with 100 applied financial framing tasks to assess how large language models (LLMs) respond under systematically varied persona conditions. Using a factorized set of 162 personas spanning gender, age, political orientation, income, and education, we analyze how persona conditioning modulates bias-consistent responding across ten instruction-tuned models. On applied tasks, persona conditioning reduces framing reversals on average and slightly increases decision confidence, with substantial variation across model families and scales. Correlation analyses further reveal that benchmark bias tendencies—particularly availability, social proof, and framing—predict applied framing sensitivity, suggesting that standardized bias scores can serve as indicators of real-world decision variability. This work provides a unified framework for linking cognitive-bias evaluation with persona-conditioned decision behavior in LLMs. (All data and prompts will be released after acceptance to preserve anonymity.)

Resources

Details