Metacognitive Myopia in Large Language Models

Understand

Large Language Models (LLMs) exhibit potentially harmful biases that reinforce culturally embedded stereotypes, influence moral judgments, or amplify positive evaluations of majority groups.

• We propose metacognitive myopia as a cognitive-ecological framework accounting for a conglomerate of established and emerging LLM biases.
• Our theoretical framework posits that biased samples in the information environment cause five symptoms of metacognitive myopia in LLMs: integration of invalid embeddings, susceptibility to redundant information, neglect of base rates in conditional computation, decision rules based on frequency, and inappropriate higher-order statistical inference for nested data structures.
• Moreover, it posits that the two main components of metacognition, monitoring and control, could account for these five symptoms.