HtmlRAG: HTML is Better Than Plain Text for Modeling Retrieved Knowledge in RAG Systems.

@inproceedings{tan-2025-htmlrag, author = {Jiejun Tan and Zhicheng Dou and Wen Wang and Mang Wang and Weipeng Chen and Ji-Rong Wen}, editor = {Guodong Long and Michale Blumestein and Yi Chang and Liane Lewin-Eytan and Zi Huang and Elad Yom-Tov}, title = {{HtmlRAG: HTML is Better Than Plain Text for Modeling Retrieved Knowledge in RAG Systems}}, booktitle = {{Proceedings of the ACM on Web Conference 2025, WWW 2025, Sydney, NSW, Australia, 28 April 2025- 2 May 2025}}, pages = {1733--1746}, publisher = {ACM}, year = {2025}, url = {https://doi.org/10.1145/3696410.3714546}, doi = {https://doi.org/10.1145/3696410.3714546} }