Do Code Models Suffer from the Dunning-Kruger Effect?
This addresses potential cognitive biases in AI-human collaboration for coding, but it is incremental as it applies a known psychological effect to AI models.
The paper investigated whether state-of-the-art LLMs exhibit the Dunning-Kruger Effect in coding tasks, finding that models show overconfidence patterns similar to humans, especially in low-resource or unfamiliar programming languages, with bias strength proportionate to model competence.
As artificial intelligence systems increasingly collaborate with humans in creative and technical domains, questions arise about the cognitive boundaries and biases that shape our shared agency. This paper investigates the Dunning-Kruger Effect (DKE), the tendency for those with limited competence to overestimate their abilities in state-of-the-art LLMs in coding tasks. By analyzing model confidence and performance across a diverse set of programming languages, we reveal that AI models mirror human patterns of overconfidence, especially in unfamiliar or low-resource domains. Our experiments demonstrate that less competent models and those operating in rare programming languages exhibit stronger DKE-like bias, suggesting that the strength of the bias is proportionate to the competence of the models.