Large language models (LLMs) have shown remarkable progress in software engineering tasks, yet their reliability in understanding and responding to code changes remains uncertain. This talk presents a critical examination of LLMs in two key areas: generating natural language for code changes (e.g., commit messages and code review comments), and comprehending human feedback in code review scenarios. We reveal that hallucinations—-misleading or inconsistent outputs-—are prevalent, affecting up to 50% of the generations. To address this, we explore metric-based detection strategies and introduce CodeReviewQA, a benchmark that decomposes code refinement into interpretable reasoning steps. Our findings highlight both the promise and limitations of current models, underscoring the need for careful evaluation to unlock their full potential in developer-facing tasks.

Patanamon Thongtanunam (or Pick) is an ARC DECRA Fellow and a lecturer at the School of Computing and Information System, The University of Melbourne. She received the D.E. degree (2016) in Information Science from Nara Institute of Science and Technology, Japan. Her primary research goals are directed towards uncovering empirical evidence and extracting knowledge from data recorded in software repositories by using statistical analysis. The foundation for her PhD thesis has been published at International Conference on Software Engineering (ICSE), International Conference on Mining Software Repositories (MSR), and International Conference on Software Analysis, Evolution, and Reengineering (SANER). More about Patanamon and her work is available online at http://patanamon.com/.