We conducted a survey of 135 software engineering (SE) practitioners to understand how they use Generative AI-based chatbots like ChatGPT for SE tasks. We find that they want to use ChatGPT for SE tasks like software library selection but often worry about the truthfulness of ChatGPT responses. We developed a suite of techniques and a tool called CID (ChatGPT Incorrectness Detector) to automatically test and detect the incorrectness in ChatGPT responses. CID is based on the iterative prompting to ChatGPT by asking it contextually similar but textually divergent questions (using an approach that utilizes metamorphic relationships in texts). The underlying principle in CID is that for a given question, a response that is different from other responses (across multiple incarnations of the question) is likely an incorrect response. In a benchmark study of library selection, we show that CID can detect incorrect responses from ChatGPT with an F1-score of 0.74 - 0.75.
Wed 17 AprDisplayed time zone: Lisbon change
11:00 - 12:30 | Generative AI studiesResearch Track / Software Engineering Education and Training at Luis de Freitas Branco Chair(s): Walid Maalej University of Hamburg | ||
11:00 15mTalk | ChatGPT Incorrectness Detection in Software Reviews Research Track Minaoar Hossain Tanzil University of Calgary, Canada, Junaed Younus Khan University of Calgary, Gias Uddin York University, Canada DOI Pre-print | ||
11:15 15mTalk | ChatGPT-Resistant Screening Instrument for Identifying Non-Programmers Research Track Raphael Serafini Ruhr University Bochum, Clemens Otto Ruhr University Bochum, Stefan Albert Horstmann Ruhr University Bochum, Alena Naiakshina Ruhr University Bochum | ||
11:30 15mTalk | Development in times of hype: How freelancers explore Generative AI? Research Track Mateusz Dolata University of Zurich, Norbert Lange Entschleunigung Lange, Gerhard Schwabe University of Zurich DOI Pre-print File Attached | ||
11:45 15mTalk | How Far Are We? The Triumphs and Trials of Generative AI in Learning Software Engineering Research Track Rudrajit Choudhuri Oregon State University, Dylan Liu Oregon State University, Igor Steinmacher Northern Arizona University, Marco Gerosa Northern Arizona University, Anita Sarma Oregon State University Pre-print | ||
12:00 15mResearch paper | Uncovering the Causes of Emotions in Software Developer Communication Using Zero-shot LLMs Research Track Mia Mohammad Imran Virginia Commonwealth University, Preetha Chatterjee Drexel University, USA, Kostadin Damevski Virginia Commonwealth University Pre-print | ||
12:15 15mTalk | Assessing AI Detectors in Identifying AI-Generated Code: Implications for Education Software Engineering Education and Training Wei Hung Pan School of Information Technology, Monash University Malaysia, Ming Jie Chok School of Information Technology, Monash University Malaysia, Jonathan Leong Shan Wong School of Information Technology, Monash University Malaysia, Yung Xin Shin School of Information Technology, Monash University Malaysia, Yeong Shian Poon School of Information Technology, Monash University Malaysia, Zhou Yang Singapore Management University, Chun Yong Chong Monash University Malaysia, David Lo Singapore Management University, Mei Kuan Lim Monash University Malaysia | ||