@article{evaluatinglargelanguagemodelsinscientifi,
  title = {Evaluating Large Language Models in Scientific Discovery},
  author = {Zhangde Song and Jieyu Lu and Yuanqi Du and Botao Yu and Thomas M. Pruyn and Yue Huang and Kehan Guo and Xiuzhe Luo and Yuanhao Qu and Yi Qu and Yinkai Wang and Haorui Wang and Jeff Guo and Jingru Gan and Parshin Shojaee and Di Luo and Andres M Bran and Gen Li and Qiyuan Zhao and Shao-Xiong Lennon Luo and Yuxuan Zhang and Xiang Zou and Wanru Zhao and Yifan F. Zhang and Wucheng Zhang and Shunan Zheng and Saiyang Zhang and Sartaaj Takrim Khan and Mahyar Rajabi-Kochi and Samantha Paradi-Maropakis and Tony Baltoiu and Fengyu Xie and Tianyang Chen and Kexin Huang and Weiliang Luo and Meijing Fang and Xin Yang and Lixue Cheng and Jiajun He and Soha Hassoun and Xiangliang Zhang and Wei Wang and Chandan K. Reddy and Chao Zhang and Zhiling Zheng and Mengdi Wang and Le Cong and Carla P. Gomes and Chang-Yu Hsieh and Aditya Nandy and Philippe Schwaller and Heather J. Kulik and Haojun Jia and Huan Sun and Seyed Mohamad Moosavi and Chenru Duan},
  year = {2025},
  eprint = {2512.15567},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2512.15567},
}