{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T13:08:55Z","timestamp":1779282535841,"version":"3.51.4"},"publisher-location":"Cham","reference-count":25,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032212887","type":"print"},{"value":"9783032212894","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-21289-4_17","type":"book-chapter","created":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T01:06:34Z","timestamp":1774314394000},"page":"257-271","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Prompt Compression in\u00a0the\u00a0Wild: Measuring Latency, Rate Adherence, and\u00a0Quality for\u00a0Faster LLM Inference"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5248-4532","authenticated-orcid":false,"given":"Cornelius","family":"Kummer","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7332-5861","authenticated-orcid":false,"given":"Lena","family":"Jurkschat","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5458-8645","authenticated-orcid":false,"given":"Michael","family":"F\u00e4rber","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7171-169X","authenticated-orcid":false,"given":"Sahar","family":"Vahdati","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,3,25]]},"reference":[{"key":"17_CR1","doi-asserted-by":"publisher","unstructured":"Bai, Y., et\u00a0al.: LongBench: a bilingual, multitask benchmark for long context understanding. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (2024). https:\/\/doi.org\/10.18653\/v1\/2024.acl-long.172","DOI":"10.18653\/v1\/2024.acl-long.172"},{"key":"17_CR2","doi-asserted-by":"crossref","unstructured":"Cheng, X., et\u00a0al.: xRAG: extreme context compression for retrieval-augmented generation with one token. In: Proceedings of the 38th International Conference on Neural Information Processing Systems, NIPS 2024 (2025). https:\/\/dl.acm.org\/doi\/10.5555\/3737916.3741392","DOI":"10.52202\/079017-3476"},{"key":"17_CR3","doi-asserted-by":"publisher","unstructured":"Chevalier, A., Wettig, A., Ajith, A., Chen, D.: Adapting language models to compress contexts. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (2023). https:\/\/doi.org\/10.18653\/v1\/2023.emnlp-main.232","DOI":"10.18653\/v1\/2023.emnlp-main.232"},{"key":"17_CR4","unstructured":"Dubey, A., Jauhri, A., Pandey, A., et\u00a0al.: The LLaMA 3 herd of models (2024). https:\/\/arxiv.org\/abs\/2407.21783"},{"key":"17_CR5","doi-asserted-by":"publisher","unstructured":"Fei, W., et\u00a0al.: Extending context window of large language models via semantic compression. In: Findings of the Association for Computational Linguistics: ACL 2024 (2024). https:\/\/doi.org\/10.18653\/v1\/2024.findings-acl.306","DOI":"10.18653\/v1\/2024.findings-acl.306"},{"key":"17_CR6","unstructured":"Ge, T., Jing, H., Wang, L., Wang, X., Chen, S.Q., Wei, F.: In-context autoencoder for context compression in a large language model. In: The Twelfth International Conference on Learning Representations (2024). https:\/\/openreview.net\/forum?id=uREj4ZuGJE"},{"key":"17_CR7","unstructured":"Hugging Face: Hugging face text generation inference (2023). https:\/\/github.com\/huggingface\/text-generation-inference"},{"key":"17_CR8","unstructured":"Jha, S., Erdogan, L.E., Kim, S., Keutzer, K., Gholami, A.: Characterizing prompt compression methods for long context inference. In: Workshop on Efficient Systems for Foundation Models II @ ICML2024 (2024). https:\/\/openreview.net\/forum?id=vs6CCDuK7l"},{"key":"17_CR9","unstructured":"Jiang, A.Q., Sablayrolles, A., Mensch, A., et\u00a0al.: Mistral 7b (2023). https:\/\/arxiv.org\/abs\/2310.06825"},{"key":"17_CR10","doi-asserted-by":"publisher","unstructured":"Jiang, H., Wu, Q., Lin, C.Y., Yang, Y., Qiu, L.: LLMLingua: compressing prompts for accelerated inference of large language models. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (2023). https:\/\/doi.org\/10.18653\/v1\/2023.emnlp-main.825","DOI":"10.18653\/v1\/2023.emnlp-main.825"},{"key":"17_CR11","doi-asserted-by":"publisher","unstructured":"Jiang, H., et\u00a0al.: LongLLMLingua: accelerating and enhancing LLMs in long context scenarios via prompt compression. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (2024). https:\/\/doi.org\/10.18653\/v1\/2024.acl-long.91","DOI":"10.18653\/v1\/2024.acl-long.91"},{"key":"17_CR12","doi-asserted-by":"publisher","first-page":"72578","DOI":"10.1109\/ACCESS.2024.3403426","volume":"12","author":"H Jung","year":"2024","unstructured":"Jung, H., Kim, K.J.: Discrete prompt compression with reinforcement learning. IEEE Access 12, 72578\u201372587 (2024). https:\/\/doi.org\/10.1109\/ACCESS.2024.3403426","journal-title":"IEEE Access"},{"key":"17_CR13","doi-asserted-by":"publisher","unstructured":"Kwon, W., et\u00a0al.: Efficient memory management for large language model serving with PagedAttention. In: Proceedings of the 29th Symposium on Operating Systems Principles. SOSP 2023 (2023). https:\/\/doi.org\/10.1145\/3600006.3613165","DOI":"10.1145\/3600006.3613165"},{"key":"17_CR14","doi-asserted-by":"publisher","unstructured":"Li, Y., Dong, B., Guerin, F., Lin, C.: Compressing context to enhance inference efficiency of large language models. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (2023). https:\/\/doi.org\/10.18653\/v1\/2023.emnlp-main.391","DOI":"10.18653\/v1\/2023.emnlp-main.391"},{"key":"17_CR15","doi-asserted-by":"publisher","unstructured":"Liu, J., Li, L., Xiang, T., Wang, B., Qian, Y.: TCRA-LLM: token compression retrieval augmented large language model for inference cost reduction. In: Findings of the Association for Computational Linguistics: EMNLP 2023 (2023). https:\/\/doi.org\/10.18653\/v1\/2023.findings-emnlp.655","DOI":"10.18653\/v1\/2023.findings-emnlp.655"},{"key":"17_CR16","doi-asserted-by":"publisher","unstructured":"Liu, Q., Wang, B., Wang, N., Mao, J.: Leveraging passage embeddings for efficient listwise reranking with large language models. In: Proceedings of the ACM on Web Conference 2025, WWW 2025 (2025). https:\/\/doi.org\/10.1145\/3696410.3714554","DOI":"10.1145\/3696410.3714554"},{"key":"17_CR17","unstructured":"Nagle, A., Girish, A., Bondaschi, M., Gastpar, M., Makkuva, A.V., Kim, H.: Fundamental limits of prompt compression: a rate-distortion framework for black-box language models. In: Proceedings of the 38th International Conference on Neural Information Processing Systems, NIPS 2024 (2024). https:\/\/dl.acm.org\/doi\/10.5555\/3737916.3740925"},{"key":"17_CR18","unstructured":"Ning, X., Lin, Z., Zhou, Z., Wang, Z., Yang, H., Wang, Y.: Skeleton-of-thought: prompting LLMs for efficient parallel generation. In: The Twelfth International Conference on Learning Representations (2024). https:\/\/openreview.net\/forum?id=mqVgBbNCm9"},{"key":"17_CR19","doi-asserted-by":"publisher","unstructured":"Pan, Z., et\u00a0al.: LLMLingua-2: data distillation for efficient and faithful task-agnostic prompt compression. In: Findings of the Association for Computational Linguistics: ACL 2024 (2024). https:\/\/doi.org\/10.18653\/v1\/2024.findings-acl.57","DOI":"10.18653\/v1\/2024.findings-acl.57"},{"key":"17_CR20","doi-asserted-by":"publisher","unstructured":"Wang, C., et\u00a0al.: Adapting LLMs for efficient context processing through soft prompt compression. In: Proceedings of the International Conference on Modeling, Natural Language Processing and Machine Learning, CMNM 2024 (2024). https:\/\/doi.org\/10.1145\/3677779.3677794","DOI":"10.1145\/3677779.3677794"},{"key":"17_CR21","unstructured":"Wang, Z., Araki, J., Jiang, Z., Parvez, M.R., Neubig, G.: Learning to filter context for retrieval-augmented generation (2023). https:\/\/arxiv.org\/abs\/2311.08377"},{"key":"17_CR22","doi-asserted-by":"publisher","unstructured":"Wolf, T., et\u00a0al.: Transformers: state-of-the-art natural language processing. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations (2020). https:\/\/doi.org\/10.18653\/v1\/2020.emnlp-demos.6","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"17_CR23","unstructured":"Xu, F., Shi, W., Choi, E.: RECOMP: improving retrieval-augmented LMs with context compression and selective augmentation. In: The Twelfth International Conference on Learning Representations (2024). https:\/\/openreview.net\/forum?id=mlJLVigNHp"},{"key":"17_CR24","unstructured":"Zhou, Z., et\u00a0al.: A survey on efficient inference for large language models (2024). https:\/\/arxiv.org\/abs\/2404.14294"},{"key":"17_CR25","doi-asserted-by":"publisher","unstructured":"Zhu, Y., et\u00a0al.: Large language models for information retrieval: a survey. ACM Trans. Inf. Syst. 44(1) (2025). https:\/\/doi.org\/10.1145\/3748304","DOI":"10.1145\/3748304"}],"container-title":["Lecture Notes in Computer Science","Advances in Information Retrieval"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-21289-4_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T12:15:02Z","timestamp":1779279302000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-21289-4_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032212887","9783032212894"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-21289-4_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"25 March 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"ECIR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Information Retrieval","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Delft","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"The Netherlands","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 March 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 April 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"48","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecir2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ecir2026.eu\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}