Prompt Compression in the Wild: Measuring Latency, Rate Adherence, and Quality for Faster LLM Inference.

@inproceedings{kummer-2026-prompt, author = {Cornelius Kummer and Lena Jurkschat and Michael F\"{a}rber and Sahar Vahdati}, editor = {Ricardo Campos and Adam Jatowt and Yanyan Lan and Mohammad Aliannejadi and Christine Bauer and Sean MacAvaney and Avishek Anand and Zhaochun Ren and Suzan Verberne and Nan Bai and Masoud Mansoury}, title = {{Prompt Compression in the Wild: Measuring Latency, Rate Adherence, and Quality for Faster LLM Inference}}, booktitle = {{Advances in Information Retrieval - 48th European Conference on Information Retrieval, ECIR 2026, Delft, The Netherlands, March 29 - April 2, 2026, Proceedings, Part I}}, series = {Lecture Notes in Computer Science}, volume = {16483}, pages = {257--271}, publisher = {Springer}, year = {2026}, url = {https://doi.org/10.1007/978-3-032-21289-4_17}, doi = {https://doi.org/10.1007/978-3-032-21289-4_17} }