Large language models have become increasingly utilized in programming contexts. However, due to the recent emergence of this trend, some aspects have been overlooked. We propose a research approach that investigates the inner mechanics of transformer networks, on a neuron, layer, and output representation level, to understand whether \textbf{there is a theoretical limitation that prevents large language models from performing optimally in a multilingual setting.} We propose to approach the investigation into the theoretical limitations, by addressing open problems in machine learning for the software engineering community. This will contribute to a greater understanding of large language models for programming-related tasks, making the findings more approachable to practitioners, and simply their implementation in future models.
Tue 16 AprDisplayed time zone: Lisbon change
14:00 - 15:30 | Focus Group: AI/ML for SEDoctoral Symposium at Fernando Pessoa Chair(s): Reyhaneh Jabbarvand University of Illinois at Urbana-Champaign | ||
14:00 90mPoster | Beyond Accuracy: Evaluating Source Code Capabilities in Large Language Models for Software Engineering Doctoral Symposium Alejandro Velasco William & Mary | ||
14:00 90mPoster | Towards Interpreting the Behavior of Large Language Models on Software Engineering Tasks Doctoral Symposium Atish Kumar Dipongkor University of Central Florida | ||
14:00 90mPoster | Programming Language Models in Multilingual Settings Doctoral Symposium Jonathan Katzy Delft University of Technology | ||
14:00 90mPoster | Beyond Accuracy and Robustness Metrics for Large Language Models for Code Doctoral Symposium | ||
14:00 90mPoster | Towards Safe, Secure, and Usable LLMs4Code Doctoral Symposium Ali Al-Kaswan Delft University of Technology, Netherlands |