FinMMR: Make Financial Numerical Reasoning More Multimodal, Comprehensive, and Challenging
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909725324476416 |
|---|---|
| author | Tang, Zichen E, Haihong Liu, Jiacheng Yang, Zhongjun Li, Rongjin Rong, Zihua He, Haoyang Hao, Zhuodi Hu, Xinyang Ji, Kun Ma, Ziyan Ji, Mengyuan Zhang, Jun Ma, Chenghao Zheng, Qianhe Liu, Yang Huang, Yiling Hu, Xinyi Huang, Qing Xie, Zijian Peng, Shiyao |
| author_facet | Tang, Zichen E, Haihong Liu, Jiacheng Yang, Zhongjun Li, Rongjin Rong, Zihua He, Haoyang Hao, Zhuodi Hu, Xinyang Ji, Kun Ma, Ziyan Ji, Mengyuan Zhang, Jun Ma, Chenghao Zheng, Qianhe Liu, Yang Huang, Yiling Hu, Xinyi Huang, Qing Xie, Zijian Peng, Shiyao |
| contents | We present FinMMR, a novel bilingual multimodal benchmark tailored to evaluate the reasoning capabilities of multimodal large language models (MLLMs) in financial numerical reasoning tasks. Compared to existing benchmarks, our work introduces three significant advancements. (1) Multimodality: We meticulously transform existing financial reasoning benchmarks, and construct novel questions from the latest Chinese financial research reports. FinMMR comprises 4.3K questions and 8.7K images spanning 14 categories, including tables, bar charts, and ownership structure charts. (2) Comprehensiveness: FinMMR encompasses 14 financial subdomains, including corporate finance, banking, and industry analysis, significantly exceeding existing benchmarks in financial domain knowledge breadth. (3) Challenge: Models are required to perform multi-step precise numerical reasoning by integrating financial knowledge with the understanding of complex financial images and text. The best-performing MLLM achieves only 53.0% accuracy on Hard problems. We believe that FinMMR will drive advancements in enhancing the reasoning capabilities of MLLMs in real-world scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_04625 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FinMMR: Make Financial Numerical Reasoning More Multimodal, Comprehensive, and Challenging Tang, Zichen E, Haihong Liu, Jiacheng Yang, Zhongjun Li, Rongjin Rong, Zihua He, Haoyang Hao, Zhuodi Hu, Xinyang Ji, Kun Ma, Ziyan Ji, Mengyuan Zhang, Jun Ma, Chenghao Zheng, Qianhe Liu, Yang Huang, Yiling Hu, Xinyi Huang, Qing Xie, Zijian Peng, Shiyao Computer Vision and Pattern Recognition Computational Engineering, Finance, and Science We present FinMMR, a novel bilingual multimodal benchmark tailored to evaluate the reasoning capabilities of multimodal large language models (MLLMs) in financial numerical reasoning tasks. Compared to existing benchmarks, our work introduces three significant advancements. (1) Multimodality: We meticulously transform existing financial reasoning benchmarks, and construct novel questions from the latest Chinese financial research reports. FinMMR comprises 4.3K questions and 8.7K images spanning 14 categories, including tables, bar charts, and ownership structure charts. (2) Comprehensiveness: FinMMR encompasses 14 financial subdomains, including corporate finance, banking, and industry analysis, significantly exceeding existing benchmarks in financial domain knowledge breadth. (3) Challenge: Models are required to perform multi-step precise numerical reasoning by integrating financial knowledge with the understanding of complex financial images and text. The best-performing MLLM achieves only 53.0% accuracy on Hard problems. We believe that FinMMR will drive advancements in enhancing the reasoning capabilities of MLLMs in real-world scenarios. |
| title | FinMMR: Make Financial Numerical Reasoning More Multimodal, Comprehensive, and Challenging |
| topic | Computer Vision and Pattern Recognition Computational Engineering, Finance, and Science |
| url | https://arxiv.org/abs/2508.04625 |