REAL-MM-RAG_FinTabTrainSet

<style>
/* H1{color:Blue !important;} */
/* H1{color:DarkOrange !important;}
H2{color:DarkOrange !important;}
H3{color:DarkOrange !important;} */
/* p{color:Black !important;} */
</style>
<!-- # REAL-MM-RAG-Bench
We introduced REAL-MM-RAG-Bench, a real-world multi-modal retrieval benchmark designed to evaluate retrieval models in reliable, challenging, and realistic settings. The benchmark was constructed using an automated pipeline, where queries were generated by a vision-language model (VLM), filtered by a large language model (LLM), and rephrased by an LLM to ensure high-quality retrieval evaluation. To simulate real-world retrieval challenges, we introduce multi-level query rephrasing, modifying queries at three distinct levels—from minor wording adjustments to significant structural changes—ensuring models are tested on their true semantic understanding rather than simple keyword matching.

### Source Paper
[REAL-MM-RAG: A Real-World Multi-Modal Retrieval Benchmark](https://arxiv.org/abs/2502.12342) -->

## REAL-MM-RAG_FinTabTrainSet
We curated a table-focused finance dataset from FinTabNet (Zheng et al., 2021), extracting richly formatted tables from S&P 500 filings. We used an automated pipeline in which queries were generated by a vision-language model (VLM) and filtered by a large language model (LLM). We generated 48,000 natural-language (query, answer, page) triplets to improve retrieval models on table-intensive financial documents.
For more information, see the project page:
https://navvewas.github.io/REAL-MM-RAG/
## Source Paper
```bibtex
@misc{wasserman2025realmmragrealworldmultimodalretrieval,
title={REAL-MM-RAG: A Real-World Multi-Modal Retrieval Benchmark},
author={Navve Wasserman and Roi Pony and Oshri Naparstek and Adi Raz Goldfarb and Eli Schwartz and Udi Barzelay and Leonid Karlinsky},
year={2025},
eprint={2502.12342},
archivePrefix={arXiv},
primaryClass={cs.IR},
url={https://arxiv.org/abs/2502.12342},
}
```

我们推出了REAL-MM-RAG-Bench，这是一个面向真实场景的多模态检索（multi-modal retrieval）基准测试集，旨在于可靠、极具挑战性且贴合现实的环境中评估检索模型。该基准测试集通过自动化流程构建：查询由视觉语言模型（vision-language model, VLM）生成，经大语言模型（large language model, LLM）筛选与重述，以保障检索评估的高质量。为模拟真实世界的检索挑战，我们引入多级查询重述机制，从三个不同层级对查询进行修改——从细微的措辞调整到大幅的结构变更，确保模型的测试基于其真正的语义理解能力，而非简单的关键词匹配。

### 源论文
[REAL-MM-RAG: A Real-World Multi-Modal Retrieval Benchmark](https://arxiv.org/abs/2502.12342)

## REAL-MM-RAG_FinTabTrainSet
我们从FinTabNet（Zheng等人，2021）中整理了一个以表格为核心的金融数据集，从标普500（S&P 500）公司的证券备案文件中提取了格式丰富的表格。我们采用自动化流程构建该数据集：查询由视觉语言模型（VLM）生成，经大语言模型（LLM）筛选。我们共生成了48000条自然语言格式的（查询、答案、页面）三元组，用于提升面向表格密集型金融文档的检索模型性能。
如需了解更多信息，请访问项目页面：
https://navvewas.github.io/REAL-MM-RAG/

## 源论文
bibtex
@misc{wasserman2025realmmragrealworldmultimodalretrieval,
title={REAL-MM-RAG: A Real-World Multi-Modal Retrieval Benchmark},
author={Navve Wasserman and Roi Pony and Oshri Naparstek and Adi Raz Goldfarb and Eli Schwartz and Udi Barzelay and Leonid Karlinsky},
year={2025},
eprint={2502.12342},
archivePrefix={arXiv},
primaryClass={cs.IR},
url={https://arxiv.org/abs/2502.12342},
}