师生风采

宋达，山东大学密码科学与工程学院助理研究员。2025年获加拿大阿尔伯塔大学电气与计算机工程系博士学位，2018年获美国明尼苏达大学计算机科学学士学位，曾于加拿大魁北克人工智能研究院（Mila）从事CIFAR AI Safety博士后研究工作。

主要研究方向为软件工程与人工智能交叉领域的可信大模型研究，涉及大语言模型的软件测试与分析新理论、AI系统生命周期的可靠性与安全性保障框架，以及面向可解释与可控智能体行为的交互式分析技术等人工智能工程化与可信性前沿问题。

研究成果发表于TSE、ICSE、ASE、CHI、NAACL等软件工程、人机交互与人工智能顶级期刊会议。

担任TSE、TOSEM、CHI、CSCW、NeurIPS等软件工程、人机交互与人工智能顶会顶刊审稿人等学术任职。

更多详情请参考个人学术主页：https://dasong-sd.github.io/。

2021.08-2025.07University of Alberta Department of Electrical and Computer Engineering理学博士

2016.08-2018.12 University of Minnesota, Twin citiesDepartment of Computer Science and Engineering 理学学士

2025.12-至今 山东大学 密码科学与工程学院 助理研究员

2025.07-2025.12魁北克人工智能研究院（Mila）CIFAR AI Safety博士后

[1]Ruoyu Sun,Da Song, Jiayang Song, Yuheng Huang, Lei Ma."TRUSTVIS: A Multi-Dimensional TrustworthinessEvaluation Framework for Large Language Models."ASE Demo Track2025.

[2]Wang Zhijie*, Zijie Zhou*,Da Song*, Yuheng Huang, Shengmai Chen, Lei Ma, and Tianyi Zhang. "Towards understanding the characteristics of code generation errors made by large language models." ICSE 2025.

[3]Da Song, Xuan Xie, Jiayang Song, Derui Zhu, Yuheng Huang, Felix Juefei-Xu, and Lei Ma. "Luna: A model-based universal analysis framework for large language models." IEEE Transactions on Software Engineering (2024).

[4]Wang Zhijie, Yuheng Huang,Da Song, Lei Ma, and Tianyi Zhang. "Promptcharm: Text-to-image generation through multi-modal prompting and refinement." CHI 2024.

[5]Da Song, Zhijie Wang, Yuheng Huang, Lei Ma, and Tianyi Zhang. "DeepLens: interactive out-of-distribution data detection in NLP models."CHI 2023.

[6]Zhijie Wang, Yuheng Huang,Da Song, Lei Ma, and Tianyi Zhang. "DeepSeer: Interactive RNN explanation and debugging via state abstraction." CHI 2023.

[7]Wang Wenhan, Chenyuan Yang, Zhijie Wang, Yuheng Huang, Zhaoyang Chu,Da Song, Lingming Zhang, An Ran Chen, and Lei Ma. "TESTEVAL: Benchmarking Large Language Models for Test Case Generation." NAACL 2025Findings.

[8]Xie Xuan, Jiayang Song, Zhehua Zhou, Yuheng Huang,Da Song, and Lei Ma. "Online safety analysis for llms: a benchmark, an assessment, and a path forward." IEEE Transactions on Artificial Intelligence (2025).