@inproceedings{he-etal-2026-large, title = "Are Large Language Models Reliable Reviewers? A Benchmark for Error Detection in Financial Documents", author = "He, Ying and Gu, Zhouhong and Hu, Zhecheng and Zhou, Yubo and Shen, Hao and Liang, Jiaqing and Dai, Zhaoqian and Shuguang, Ma and Yu, Fei and Xiao, Yanghua and Li, Zhixu", editor = "Liakata, Maria and Moreira, Viviane P. and Zhang, Jiajun and Jurgens, David", booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026", month = jul, year = "2026", address = "San Diego, California, United States", publisher = "Association for Computational Linguistics", url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.1481/", pages = "29625--29643", ISBN = "979-8-89176-395-1" }