MME-Finance
收藏MME-Finance: 多模态金融基准数据集
概述
- 名称: MME-Finance
- 类型: 多模态金融基准数据集
- 语言: 中英双语
- 问题数量: 1,171个英文问题和1,103个中文问题
- 领域: 金融
- 特点:
- 涵盖多种金融图像类型和多模态能力
- 提出了一种详细的评估策略,考虑图像因素,与人类评估高度一致
数据集亮点
- 双语多模态金融基准: 首个双语多模态金融基准,涵盖多种金融图像类型和多模态能力。
- 评估策略: 提出了一种详细的评估策略,考虑图像因素,与人类评估高度一致。
- 有价值的见解: 基于MME-Finance对19个多模态大语言模型进行了广泛评估,揭示了当前模型在金融应用中的优缺点。
使用方法
-
数据下载: 需下载
MMfin.tsv和MMfin_CN.tsv文件以及相关金融图像。 -
文件结构:
├─ datasets ├─ images ├─ MMfin ... ├─ MMfin_CN ... │ MMfin.tsv │ MMfin_CN.tsv
-
推理与评估:
export LMUData="The path of the datasets" python run.py --data MMfin --model Qwen2-VL-2B-Instruct --verbose python run.py --data MMfin_CN --model Qwen2-VL-2B-Instruct --verbose
数据集状态
- 当前发布: 已发布110个中英双语样本。
- 未来计划: 预计一个月内发布所有数据。
性能表现
-
Qwen2-VL-72B在MMfin上的表现:
"Category","tot","acc" "Accurate Numerical Calculation","10","100.0" "Entity Recognition","10","68.0" "Explain Reason","10","82.0" "Financial Knowledge","10","80.0" "Image Caption","10","78.0" "Investment Advice","10","64.0" "Not Applicable","10","90.0" "Numerical Calculation","10","48.0" "OCR","10","66.0" "Risk Warning","10","88.0" "Spatial Awareness","10","52.0" "Overall","110","74.18181818181819"
-
Qwen2-VL-72B在MMfin_CN上的表现:
"Category","tot","acc" "Accurate Numerical Calculation","10","80.0" "Entity Recognition","10","66.0" "Explain Reason","10","78.0" "Financial Knowledge","10","86.0" "Image Caption","10","100.0" "Investment Advice","10","76.0" "Not Applicable","10","46.0" "Numerical Calculation","10","60.0" "OCR","10","82.0" "Risk Warning","10","84.0" "Spatial Awareness","10","58.0" "Overall","110","74.18181818181819"
引用
@article{gan2024woodpecker, title={MME-Finance: A Multimodal Finance Benchmark for Expert-level Understanding and Reasoning}, author={Gan, Ziliang and Lu, Yu and Zang, Dong and Li, Haohan and Liu, Che and Liu, Jian and Liu, Ji and Wu, Haipang and Fu, Chaoyou and Xu, Zenglin and Zhang, Rongjunchen and Dai, Yong}, journal={arXiv preprint arXiv:2411.03314}, year={2024} }
许可证
- 代码许可证: Apache 2.0
- 数据许可证: CC BY NC 4.0
- 使用限制: 数据和代码仅用于研究目的。




