@inproceedings{L42025FSE,
author = {Jiang, Zhihan and Huang, Junjie and Yu, Guangba and Chen, Zhuangbin and Li, Yichen and Zhong, Renyi and Feng, Cong and Yang, Yongqiang and Yang, Zengyin and Lyu, Michael},
title = {L4: Diagnosing Large-scale LLM Training Failures via Automated Log Analysis},
year = {2025},
isbn = {9798400712760},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3696630.3728531},
doi = {10.1145/3696630.3728531},
booktitle = {Proceedings of the 33rd ACM International Conference on the Foundations of Software Engineering},
pages = {51–63},
}