Do Code Models Suffer from the Dunning-Kruger Effect?

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Singh, Mukul, Chatterjee, Somya, Radhakrishna, Arjun, Gulwani, Sumit
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912632551768064
author Singh, Mukul
Chatterjee, Somya
Radhakrishna, Arjun
Gulwani, Sumit
author_facet Singh, Mukul
Chatterjee, Somya
Radhakrishna, Arjun
Gulwani, Sumit
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_05457
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Do Code Models Suffer from the Dunning-Kruger Effect?
Singh, Mukul
Chatterjee, Somya
Radhakrishna, Arjun
Gulwani, Sumit
Artificial Intelligence
Computation and Language
Software Engineering
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.
title Do Code Models Suffer from the Dunning-Kruger Effect?
topic Artificial Intelligence
Computation and Language
Software Engineering
url https://arxiv.org/abs/2510.05457