MMFCTUB: Multi-Modal Financial Credit Table Understanding Benchmark
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866918280853192704 |
|---|---|
| author | Yakun, Cui Zhang, Yanting Lei, Zhu Xie, Jian Kou, Zhizhuo Du, Hang Zhu, Zhenghao Han, Sirui |
| author_facet | Yakun, Cui Zhang, Yanting Lei, Zhu Xie, Jian Kou, Zhizhuo Du, Hang Zhu, Zhenghao Han, Sirui |
| contents | The advent of multi-modal language models (MLLMs) has spurred research into their application across various table understanding tasks. However, their performance in credit table understanding (CTU) for financial credit review remains largely unexplored due to the following barriers: low data consistency, high annotation costs stemming from domain-specific knowledge and complex calculations, and evaluation paradigm gaps between benchmark and real-world scenarios. To address these challenges, we introduce MMFCTUB (Multi-Modal Financial Credit Table Understanding Benchmark), a practical benchmark, encompassing more than 7,600 high quality CTU samples across 5 table types. MMFCTUB employ a minimally supervised pipeline that adheres to inter-table constraints and maintains data distributions consistency. The benchmark leverages capacity-driven questions and mask-and-recovery strategy to evaluate models' cross-table structure perception, domain knowledge utilization, and numerical calculation capabilities. Utilizing MMFCTUB, we conduct comprehensive evaluations of both proprietary and open-source MLLMs, revealing their strengths and limitations in CTU tasks. MMFCTUB serves as a valuable resource for the research community, facilitating rigorous evaluation of MLLMs in the domain of CTU. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_04643 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | MMFCTUB: Multi-Modal Financial Credit Table Understanding Benchmark Yakun, Cui Zhang, Yanting Lei, Zhu Xie, Jian Kou, Zhizhuo Du, Hang Zhu, Zhenghao Han, Sirui Computational Engineering, Finance, and Science The advent of multi-modal language models (MLLMs) has spurred research into their application across various table understanding tasks. However, their performance in credit table understanding (CTU) for financial credit review remains largely unexplored due to the following barriers: low data consistency, high annotation costs stemming from domain-specific knowledge and complex calculations, and evaluation paradigm gaps between benchmark and real-world scenarios. To address these challenges, we introduce MMFCTUB (Multi-Modal Financial Credit Table Understanding Benchmark), a practical benchmark, encompassing more than 7,600 high quality CTU samples across 5 table types. MMFCTUB employ a minimally supervised pipeline that adheres to inter-table constraints and maintains data distributions consistency. The benchmark leverages capacity-driven questions and mask-and-recovery strategy to evaluate models' cross-table structure perception, domain knowledge utilization, and numerical calculation capabilities. Utilizing MMFCTUB, we conduct comprehensive evaluations of both proprietary and open-source MLLMs, revealing their strengths and limitations in CTU tasks. MMFCTUB serves as a valuable resource for the research community, facilitating rigorous evaluation of MLLMs in the domain of CTU. |
| title | MMFCTUB: Multi-Modal Financial Credit Table Understanding Benchmark |
| topic | Computational Engineering, Finance, and Science |
| url | https://arxiv.org/abs/2601.04643 |