P PaperCompassAI 论文工作台
← 返回论文检索
ACL 2026longmain

MultiFinBen: Benchmarking Large Language Models for Multilingual and Multimodal Financial Application

Xueqing Peng, Lingfei Qian, Yan Wang, Ruoyu Xiang, Yueru He, Yang Ren, Mingyang Jiang, Vincent Jim Zhang, Yuqing Guo, Jeff Zhao, Huan He, Yi Han, Yun Feng, Yuechen Jiang, Yupeng Cao, Haohang Li, Yangyang Yu, Xiaoyu Wang, Penglei Gao, Shengyuan Lin, Keyi Wang, Shanshan Yang, Yilun Zhao, Zhiwei Liu, Peng Lu, Jerry Huang, Suyuchen Wang, Triantafillos Papadopoulos, Polydoros Giannouris, Efstathia Soufleri, Nuo Chen, Zhiyang Deng, Heming Fu, Yijia Zhao, Mingquan Lin, Meikang Qiu, Kaleb E Smith, Arman Cohan, Xiao-Yang Liu, Jimin Huang, Guojun Xiong, Alejandro Lopez-Lira, Xi Chen, Junichi Tsujii, Jian-Yun Nie, Sophia Ananiadou, Qianqian Xie

Yale University · Columbia University · Accenture · cleveland clinic foundation · Stevens Institute of Technology · Athens University of Economics and Business and Athena Research and Innovation Centre · University of Manchester · Athena Research and Innovation Center · National University of Singapore · University of Massachusetts Boston · University of Minnesota - Twin Cities · Augusta University · Yale University and Allen Institute for Artificial Intelligence · University of Manchester and The Fin AI · Harvard University · University of Florida · New York University · National Institute of Advanced Industrial Science and Technology · University of Montreal · Wuhan University

查看 PDF ↗ 论文页面 ↗ 登录后记笔记

PDF 由论文原始站点提供，PaperCompass 不保存论文文件。DOI 10.18653/v1/2026.acl-long.770 ↗

摘要

Real-world financial analysis involves information across multiple languages and modalities, from reports and news to scanned filings and meeting recordings. Yet most existing evaluations of LLMs in finance remain text-only, monolingual, and largely saturated by current models. To bridge these gaps, we present MultiFinBen, the first expert-annotated multilingual (five languages) and multimodal (text, vision, audio) benchmark for evaluating LLMs in realistic financial contexts. MultiFinBen introduces two new task families: multilingual financial reasoning, which tests cross-lingual evidence integration from filings and news, and financial OCR, which extracts structured text from scanned documents containing tables and charts. Rather than aggregating all available datasets, we apply a structured, difficulty-aware selection based on advanced model performance, ensuring balanced challenge and removing redundant tasks. Evaluating 21 leading LLMs shows that even frontier multimodal models like GPT-4o achieve only 46.01% overall, stronger on vision and audio but dropping sharply in multilingual settings. These findings expose persistent limitations in multilingual, multimodal, and expert-level financial reasoning. All datasets, evaluation scripts, and leaderboards are publicly released.