@misc{tan2024htmlrag, title={HtmlRAG: HTML is Better Than Plain Text for Modeling Retrieved Knowledge in RAG Systems}, author={Jiejun Tan and Zhicheng Dou and Wen Wang and Mang Wang and Weipeng Chen and Ji-Rong Wen}, year={2024}, eprint={2411.02959}, archivePrefix={arXiv}, primaryClass={cs.IR}, doi={10.1145/3696410.3714546}, url={https://arxiv.org/abs/2411.02959} }