Understanding Large Language Model Performance in Software Engineering: A Large-scale Question Answering Benchmark.

@inproceedings{hu-2025-understanding, author = {Ruida Hu and Chao Peng and Jingyi Ren and Bo Jiang and Xiangxin Meng and Qinyun Wu and Pengfei Gao and Xinchen Wang and Cuiyun Gao}, editor = {Nicola Ferro and Maria Maistro and Gabriella Pasi and Omar Alonso and Andrew Trotman and Suzan Verberne}, title = {{Understanding Large Language Model Performance in Software Engineering: A Large-scale Question Answering Benchmark}}, booktitle = {{Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2025, Padua, Italy, July 13-18, 2025}}, pages = {3025--3029}, publisher = {ACM}, year = {2025}, url = {https://doi.org/10.1145/3726302.3730262}, doi = {https://doi.org/10.1145/3726302.3730262} }