{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T10:36:06Z","timestamp":1763202966802,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":27,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819617098"},{"type":"electronic","value":"9789819617104"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-981-96-1710-4_11","type":"book-chapter","created":{"date-parts":[[2025,1,31]],"date-time":"2025-01-31T09:57:13Z","timestamp":1738317433000},"page":"136-148","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["QUITO: Accelerating Long-Context Reasoning Through Query-Guided Context Compression"],"prefix":"10.1007","author":[{"given":"Wenshan","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yihang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yixing","family":"Fan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huaming","family":"Liao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiafeng","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,2,1]]},"reference":[{"doi-asserted-by":"crossref","unstructured":"Arefeen, M.A., Debnath, B., Chakradhar, S.: Leancontext: cost-efficient domain-specific question answering using llms (2023). https:\/\/arxiv.org\/abs\/2309.00841","key":"11_CR1","DOI":"10.1016\/j.nlp.2024.100065"},{"unstructured":"Asai, A., Wu, Z., Wang, Y., Sil, A., Hajishirzi, H.: Self-rag: learning to retrieve, generate, and critique through self-reflection (2023). https:\/\/arxiv.org\/abs\/2310.11511","key":"11_CR2"},{"unstructured":"Borgeaud, S., et al.: Improving language models by retrieving from trillions of tokens (2022). https:\/\/arxiv.org\/abs\/2112.04426","key":"11_CR3"},{"unstructured":"Brown, T.B., et\u00a0al.: Language models are few-shot learners. arXiv preprint arXiv:2005.14165 (2020)","key":"11_CR4"},{"unstructured":"Chaudhari, S., Mithal, V., Polatkan, G., Ramanath, R.: An attentive survey of attention models (2021). https:\/\/arxiv.org\/abs\/1904.02874","key":"11_CR5"},{"unstructured":"Dong, Q., et al.: A survey on in-context learning (2024). https:\/\/arxiv.org\/abs\/2301.00234","key":"11_CR6"},{"doi-asserted-by":"publisher","unstructured":"Gao, T., Yen, H., Yu, J., Chen, D.: Enabling large language models to generate text with citations. In: Bouamor, H., Pino, J., Bali, K. (eds.) Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pp. 6465\u20136488. Association for Computational Linguistics, Singapore, December 2023. https:\/\/doi.org\/10.18653\/v1\/2023.emnlp-main.398. https:\/\/aclanthology.org\/2023.emnlp-main.398","key":"11_CR7","DOI":"10.18653\/v1\/2023.emnlp-main.398"},{"unstructured":"Gao, Y., et al.: Retrieval-augmented generation for large language models: a survey (2024)","key":"11_CR8"},{"unstructured":"Jiang, H., et al.: Longllmlingua: accelerating and enhancing llms in long context scenarios via prompt compression. ArXiv preprint abs\/2310.06839 (2023). https:\/\/arxiv.org\/abs\/2310.06839","key":"11_CR9"},{"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: Bouamor, H., Pino, J., Bali, K. (eds.) Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pp. 13358\u201313376. Association for Computational Linguistics, Singapore, December 2023. https:\/\/doi.org\/10.18653\/v1\/2023.emnlp-main.825. https:\/\/aclanthology.org\/2023.emnlp-main.825","key":"11_CR10","DOI":"10.18653\/v1\/2023.emnlp-main.825"},{"doi-asserted-by":"crossref","unstructured":"Li, Y., Dong, B., Lin, C., Guerin, F.: Compressing context to enhance inference efficiency of large language models (2023)","key":"11_CR11","DOI":"10.18653\/v1\/2023.emnlp-main.391"},{"unstructured":"Lin, C.Y.: ROUGE: a package for automatic evaluation of summaries. In: Text Summarization Branches Out, pp. 74\u201381. Association for Computational Linguistics, Barcelona, Spain, July 2004. https:\/\/aclanthology.org\/W04-1013","key":"11_CR12"},{"unstructured":"Liu, J., Jin, J., Wang, Z., Cheng, J., Dou, Z., Wen, J.R.: Reta-llm: a retrieval-augmented large language model toolkit (2023). https:\/\/arxiv.org\/abs\/2306.05212","key":"11_CR13"},{"doi-asserted-by":"crossref","unstructured":"Liu, N.F., et al.: Lost in the middle: How language models use long contexts (2023). arXiv:2307.03172","key":"11_CR14","DOI":"10.1162\/tacl_a_00638"},{"doi-asserted-by":"publisher","unstructured":"Mao, Y., Dong, X., Xu, W., Gao, Y., Wei, B., Zhang, Y.: Fit-rag: black-box rag with factual information and token reduction. ACM Trans. Inf. Syst., July 2024. https:\/\/doi.org\/10.1145\/3676957. Just Accepted","key":"11_CR15","DOI":"10.1145\/3676957"},{"unstructured":"de\u00a0Santana\u00a0Correia, A., Colombini, E.L.: Attention, please! a survey of neural attention models in deep learning (2021). https:\/\/arxiv.org\/abs\/2103.16775","key":"11_CR16"},{"unstructured":"Song, Y., Wang, T., Mondal, S.K., Sahoo, J.P.: A comprehensive survey of few-shot learning: evolution, applications, challenges, and opportunities (2022). https:\/\/arxiv.org\/abs\/2205.06743","key":"11_CR17"},{"doi-asserted-by":"publisher","unstructured":"Stelmakh, I., Luan, Y., Dhingra, B., Chang, M.W.: ASQA: factoid questions meet long-form answers. In: Goldberg, Y., Kozareva, Z., Zhang, Y. (eds.) Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pp. 8273\u20138288. Association for Computational Linguistics, Abu Dhabi, United Arab Emirates, December 2022. https:\/\/doi.org\/10.18653\/v1\/2022.emnlp-main.566. https:\/\/aclanthology.org\/2022.emnlp-main.566","key":"11_CR18","DOI":"10.18653\/v1\/2022.emnlp-main.566"},{"unstructured":"Su, W., Tang, Y., Ai, Q., Wu, Z., Liu, Y.: Dragin: dynamic retrieval augmented generation based on the real-time information needs of large language models. ArXiv abs\/2403.10081 (2024). https:\/\/api.semanticscholar.org\/CorpusID:268509926","key":"11_CR19"},{"unstructured":"Touvron, H., et al.: Llama: open and efficient foundation language models (2023). https:\/\/arxiv.org\/abs\/2302.13971","key":"11_CR20"},{"doi-asserted-by":"crossref","unstructured":"Trivedi, H., Balasubramanian, N., Khot, T., Sabharwal, A.: Interleaving retrieval with chain-of-thought reasoning for knowledge-intensive multi-step questions (2023). https:\/\/arxiv.org\/abs\/2212.10509","key":"11_CR21","DOI":"10.18653\/v1\/2023.acl-long.557"},{"unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., Polosukhin, I.: Attention is all you need. In: Proceedings of the 31st International Conference on Neural Information Processing Systems (NeurIPS), pp. 6000\u20136010 (2017)","key":"11_CR22"},{"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":"11_CR23"},{"unstructured":"Wei, J., et al.: Chain-of-thought prompting elicits reasoning in large language models (2023). https:\/\/arxiv.org\/abs\/2201.11903","key":"11_CR24"},{"unstructured":"Xu, F., Shi, W., Choi, E.: Recomp: Improving retrieval-augmented lms with compression and selective augmentation. ArXiv abs\/2310.04408 (2023). https:\/\/api.semanticscholar.org\/CorpusID:263830734","key":"11_CR25"},{"unstructured":"Xu, Z., et al.: Compress, then prompt: improving accuracy-efficiency trade-off of llm inference with transferable prompt (2023). https:\/\/arxiv.org\/abs\/2305.11186","key":"11_CR26"},{"unstructured":"Yang, A., et al.: Baichuan 2: open large-scale language models (2023). https:\/\/arxiv.org\/abs\/2309.10305","key":"11_CR27"}],"container-title":["Lecture Notes in Computer Science","Information Retrieval"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-1710-4_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,31]],"date-time":"2025-01-31T09:57:26Z","timestamp":1738317446000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-1710-4_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819617098","9789819617104"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-1710-4_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"1 February 2025","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":"CCIR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China Conference on Information Retrieval","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Wuhan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccir2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.cips-ir.org.cn\/CCIR2024\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}