Exploring the Evidence-Based SE Beliefs of Generative AI Tools

TL;DR

This study investigates how generative AI tools used in software engineering perceive evidence-based practices, revealing their ambiguous beliefs and lack of credible support for empirical research claims, which impacts their reliability.

Contribution

It provides the first evaluation of AI tools' beliefs about evidence-based SE claims, highlighting gaps and guiding future improvements for trustworthy AI integration.

Findings

AI tools show ambiguous beliefs about research claims

Lack of credible evidence supporting AI responses

Implications for improving AI trustworthiness in SE

Abstract

Background: Recent innovations in generative artificial intelligence (AI) have transformed how programmers develop and maintain software. The advanced capabilities of generative AI tools in supporting development tasks have led to a rise in their adoption within software engineering (SE) workflows. However, little is known about how AI tools perceive evidence-based practices supported by empirical SE research. Aim: To this end, we explore the "beliefs" of generative AI tools increasingly used to support software development in practice. Method: We conduct a preliminary evaluation conceptually replicating prior work to investigate 17 evidence-based claims across five generative AI tools. Results: Our findings demonstrate generative AI tools have ambiguous beliefs regarding research claims and lack credible evidence to support responses. Conclusions: Based on our results, we provide implications for practitioners integrating generative AI-based systems into development contexts and shed light on future research directions to enhance the reliability and trustworthiness of generative AI -- aiming to increase awareness and adoption of evidence-based SE research findings in practice.