Don't Do RAG: When Cache-Augmented Generation is All You Need for Knowledge Tasks.

@inproceedings{chan-2025-dont, author = {Brian J. Chan and Chao-Ting Chen and Jui-Hung Cheng and Hen-Hsen Huang}, editor = {Guodong Long and Michale Blumestein and Yi Chang and Liane Lewin-Eytan and Zi Huang and Elad Yom-Tov}, title = {{Don't Do RAG: When Cache-Augmented Generation is All You Need for Knowledge Tasks}}, booktitle = {{Companion Proceedings of the ACM on Web Conference 2025, WWW 2025, Sydney, NSW, Australia, 28 April 2025 - 2 May 2025}}, pages = {893--897}, publisher = {ACM}, year = {2025}, url = {https://doi.org/10.1145/3701716.3715490}, doi = {https://doi.org/10.1145/3701716.3715490} }