Zhang et al. "LLMEval: A Preliminary Study on How to Evaluate Large Language Models." AAAI Conference on Artificial Intelligence, 2024. doi:10.1609/AAAI.V38I17.29934
Markdown
[Zhang et al. "LLMEval: A Preliminary Study on How to Evaluate Large Language Models." AAAI Conference on Artificial Intelligence, 2024.](https://mlanthology.org/aaai/2024/zhang2024aaai-llmeval/) doi:10.1609/AAAI.V38I17.29934
BibTeX
@inproceedings{zhang2024aaai-llmeval,
title = {{LLMEval: A Preliminary Study on How to Evaluate Large Language Models}},
author = {Zhang, Yue and Zhang, Ming and Yuan, Haipeng and Liu, Shichun and Shi, Yongyao and Gui, Tao and Zhang, Qi and Huang, Xuanjing},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2024},
pages = {19615-19622},
doi = {10.1609/AAAI.V38I17.29934},
url = {https://mlanthology.org/aaai/2024/zhang2024aaai-llmeval/}
}