Da Song
song.da.872[at]gmail[dot]com.
I’m a CIFAR AI Safety Postdoctoral Fellow at Quebec AI Institute (Mila), working under the supervision of Dr. Foutse Khomh, with Dr. Lei Ma and Dr. Randy Goebel as co-supervisors.
I obtained my Ph.D. from the University of Alberta in 2025 under the supervision of Dr. Lei Ma. Before that, I earned a B.S. in Computer Science from the University of Minnesota, Twin Cities.
My research focuses on the quality assurance of LLM-based systems, emphasizing testing, analysis, and behavioral monitoring. I’m particularly interested in the trustworthiness of large language models, robust AI system design, and HCI-driven approaches to AI system development. I’ve also had the pleasure of collaborating with Dr. Tianyi Zhang on SE & HCI related topics.
I’m always open to discussing new research ideas, collaborations, and opportunities in the field of software engineering and AI. Feel free to reach out via email or connect with me on LinkedIn.
NEWS
| Sep 11, 2025 | One paper was accepted by ASE 2025 Demo track! Congratulations to Ruoyu. |
|---|---|
| Jul 28, 2025 | I have joined Mila as a Postdoctoral Fellow to continue my research on trustworthy and reliable AI systems. |
| Jun 26, 2025 | I have successfully passed my Ph.D. Final Defense! Feel free to call me Dr. Song now 😉. |
| Jan 30, 2025 | Two papers were accepted by ICSE 2025. See you in Ottawa 🇨🇦! |
SELECTED PUBLICATIONS
-
Towards Understanding the Characteristics of Code Generation Errors Made by Large Language ModelsIn 2025 IEEE/ACM 47th International Conference on Software Engineering (ICSE), 2025 -
Luna: A model-based universal analysis framework for large language modelsIEEE Transactions on Software Engineering, 2024 -
DeepLens: interactive out-of-distribution data detection in NLP modelsIn Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems, 2023