AI + SE Seminar Series: Reyhan Jabbarvand Behrouz
Beyond Crafted Benchmarks, Using LLMs to Automate Software Engineering Tasks in Real-World Projects
Large Language Models (LLMs) are the new automation technology to explore for software development and maintenance. State-of-the-art LLMs and techniques leveraging them for code-related tasks are mostly evaluated on crafted benchmarks (mostly not reflective of the complexity of real-world projects) and under very simple tasks (even if the studied programs are real-world projects, the tasks are very simple). In this presentation, I will first talk about the challenges of using LLMs for (1) whole-repository code translation and (2) code synthesis for repairing test flakiness in real-world projects. After discussing such challenges, I will talk about how neuro-symbolic approaches that combine the generalizability of LLMs and the soundness of program analysis can overcome these challenges.
Bio
Reyhan Jabbarvand is an Assistant Professor of Computer Science at the University of Illinois, Urbana-Champaign. Her research interests lie at the intersection of Program Analysis and Artificial Intelligence. Reyhan received her PhD from the University of California, Irvine, where her research on energy testing of mobile applications was recognized by a Google PhD Fellowship. As a faculty, she has been the recipient of the NSF CAREER award, and her research has been supported by grants from NSF, IBM, and C3.ai.
For more details, please visit: https://reyhaneh.cs.illinois.edu/