leomessizhang/HtmlRAG-test

---
license: mit
task_categories:
- question-answering
language:
- en
size_categories:
- 1K<n<10K
---

## Dataset Information
We release the test data used in **HtmlRAG: HTML is Better Than Plain Text for Modeling Retrieval Results in RAG Systems**. The test data is sampled from 6 widely used QA datasets, including ASQA, Hotpot-QA, NQ, Trivia-QA, MuSiQue, and ELI5. You can access the original dataset [here](https://huggingface.co/datasets/RUC-NLPIR/FlashRAG_datasets).
We apply Bing search API in the US-EN region to search for relevant web pages, and then we scrap static HTML documents through URLs in returned search results. We provide the URLs and corresponding HTML documents in our experiments for reproduction.

<p align="left">
Useful links: 📝 <a href="https://arxiv.org/abs/2411.02959" target="_blank">Paper</a> • 🤗 <a href="https://huggingface.co/papers/2411.02959" target="_blank">Hugging Face</a> • 🧩 <a href="https://github.com/plageon/HtmlRAG" target="_blank">Github</a>
</p>

We propose HtmlRAG, which uses HTML instead of plain text as the format of external knowledge in RAG systems. To tackle the long context brought by HTML, we propose **Lossless HTML Cleaning** and **Two-Step Block-Tree-Based HTML Pruning**.

- **Lossless HTML Cleaning**: This cleaning process just removes totally irrelevant contents and compress redundant structures, retaining all semantic information in the original HTML. The compressed HTML of lossless HTML cleaning is suitable for RAG systems that have long-context LLMs and are not willing to loss any information before generation.

- **Two-Step Block-Tree-Based HTML Pruning**: The block-tree-based HTML pruning consists of two steps, both of which are conducted on the block tree structure. The first pruning step uses a embedding model to calculate scores for blocks, while the second step uses a path generative model. The first step processes the result of lossless HTML cleaning, while the second step processes the result of the first pruning step.

🌹 If you use this model, please ✨star our **[GitHub repository](https://github.com/plageon/HtmlRAG)** to support us. Your star means a lot!