Cognitive Biases in LLM-Assisted Software Development

TL;DR

This study investigates how cognitive biases influence decision-making in LLM-assisted software development, revealing that nearly half of developer actions are biased, with over half linked to LLM interactions, and proposes mitigation strategies.

Contribution

It is the first comprehensive analysis of cognitive biases in AI-assisted programming, identifying 15 bias categories and providing a taxonomy validated by psychologists.

Findings

48.8% of programmer actions are biased

56.4% of biased actions involve LLM interactions

Introduction of a taxonomy of 15 bias categories

Abstract

The widespread adoption of Large Language Models (LLMs) in software development is transforming programming from a solution-generative to a solution-evaluative activity. This shift opens a pathway for new cognitive challenges that amplify existing decision-making biases or create entirely novel ones. One such type of challenge stems from cognitive biases, which are thinking patterns that lead people away from logical reasoning and result in sub-optimal decisions. How do cognitive biases manifest and impact decision-making in emerging AI-collaborative development? This paper presents the first comprehensive study of cognitive biases in LLM-assisted development. We employ a mixed-methods approach, combining observational studies with 14 student and professional developers, followed by surveys with 22 additional developers. We qualitatively compare categories of biases affecting developers against the traditional non-LLM workflows. Our findings suggest that LLM-related actions are more likely to be associated with novel biases. Through a systematic analysis of 90 cognitive biases specific to developer-LLM interactions, we develop a taxonomy of 15 bias categories validated by cognitive psychologists. We found that 48.8% of total programmer actions are biased, and developer-LLM interactions account for 56.4% of these biased actions. We discuss how these bias categories manifest, present tools and practices for developers, and recommendations for LLM tool builders to help mitigate cognitive biases in human-AI programming.