Exploring the Evidence-Based Beliefs of LLM-Based Programming Assistants
This program is tentative and subject to change.
Recent innovations in artificial intelligence (AI), primarily powered by large language models (LLMs), have transformed how programmers develop and maintain software—leading to new frontiers in software engineering (SE). The advanced capabilities of LLM-based programming assistants to support software development tasks have led to a rise in the adoption of LLMs in SE. However, little is known about the evidenced-based practices, tools and processes verified by research findings, supported and adopted by AI programming assistants. To this end, our work conducts a preliminary evaluation exploring the textit{beliefs} of LLM used to support software development tasks. We investigate 17 evidence-based claims posited by empirical SE research across five LLM-based programming assistants. Our findings show that LLM-based programming assistants have ambiguous beliefs regarding research claims and lack credible evidence to support responses. Based on our results, we provide implications for practitioners adopting LLM-based programming assistants in development contexts and shed light on future research directions to enhance the reliability and trustworthiness of LLMs—aiming to increase awareness and adoption of evidence-based SE research findings in practice.
This program is tentative and subject to change.
Thu 2 OctDisplayed time zone: Hawaii change
10:10 - 11:10 | Evidence and Research Quality in Software EngineeringESEM - Technical Track / ESEM - Emerging Results and Vision Track / ESEM - Journal First Track / at Kaiulani II Chair(s): Mika Mäntylä University of Helsinki and University of Oulu | ||
10:10 15mTalk | Cognitive Biases in Software Engineering: Debiasing through Reconception ESEM - Emerging Results and Vision Track | ||
10:25 15mTalk | Exploring the Evidence-Based Beliefs of LLM-Based Programming Assistants ESEM - Emerging Results and Vision Track | ||
10:40 15mTalk | Research artifacts for human-oriented experiments in software engineering: An ACM badges-driven structure proposal ESEM - Journal First Track Cathy Guevara-Vega Universidad Técnica del Norte, Beatriz Bernárdez University of Seville, Margarita Cruz Risco University of Seville, Amador Durán University of Seville, Antonio Ruiz-Cortés University of Seville, Martín Solari Universidad ORT Uruguay | ||
10:55 15mTalk | Aggregating empirical evidence from data strategies studies: a case on model quantization ESEM - Technical Track Santiago del Rey Universitat Politècnica De Catalunya - Barcelona Tech, Paulo Sérgio Medeiros Federal University of the State of Rio de Janeiro (UNIRIO), Guilherme Horta Travassos Federal University of Rio de Janeiro, Xavier Franch Universitat Politècnica de Catalunya, Silverio Martínez-Fernández UPC-BarcelonaTech Pre-print |