@article{corallo-papotti-2024-finch, title = "{FINCH}: Prompt-guided Key-Value Cache Compression for Large Language Models", author = "Corallo, Giulio and Papotti, Paolo", journal = "Transactions of the Association for Computational Linguistics", volume = "12", year = "2024", address = "Cambridge, MA", publisher = "MIT Press", url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2024.tacl-1.83/", doi = "10.1162/tacl_a_00716", pages = "1517--1532" }