{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T01:37:52Z","timestamp":1780450672397,"version":"3.54.1"},"publisher-location":"Singapore","reference-count":34,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819756629","type":"print"},{"value":"9789819756636","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-981-97-5663-6_19","type":"book-chapter","created":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T01:10:40Z","timestamp":1722474640000},"page":"221-232","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Context Compression and Extraction: Efficiency Inference of Large Language Models"],"prefix":"10.1007","author":[{"given":"Junyao","family":"Zhou","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruiqing","family":"Du","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yushan","family":"Tan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jintao","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zonghao","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhunchen","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xian","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenpeng","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,8,1]]},"reference":[{"key":"19_CR1","unstructured":"Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J.D., Dhariwal, et al.: Language models are few-shot learners. In: Advances in Neural Information Processing Systems, vol. 33, pp. 1877\u20131901 (2020)"},{"key":"19_CR2","unstructured":"Wang, Y., et al.: Aligning large language models with human: a survey. arXiv preprint arXiv:2307.12966 (2023)"},{"key":"19_CR3","unstructured":"Gao, Y., et al.: Retrieval-augmented generation for large language models: a survey. arXiv preprint arXiv:2312.10997 (2023)"},{"key":"19_CR4","unstructured":"Zhou, W., et al.: RecurrentGPT: interactive generation of (arbitrarily) long text. arXiv preprint arXiv:2305.13304 (2023)"},{"key":"19_CR5","unstructured":"Liang, X., et al.: Unleashing infinite-length input capacity for large-scale language models with self-controlled memory system. arXiv preprint arXiv:2304.13343 (2023)"},{"key":"19_CR6","unstructured":"Beltagy, I., Peters, M.E., Cohan, A.: Longformer: the long-document transformer. arXiv preprint arXiv:2004.05150 (2020)"},{"key":"19_CR7","unstructured":"Hu, E.J., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., et al.: LoRA: low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)"},{"key":"19_CR8","unstructured":"Dettmers, T., Lewis, M., Belkada, Y., Zettlemoyer, L.: GPT3. int8 (): 8-bit matrix multiplication for transformers at scale. In: Advances in Neural Information Processing Systems, vol. 35, pp. 30318\u201330332 (2022)"},{"key":"19_CR9","unstructured":"Taori, R., et al.: Stanford alpaca: an instruction-following llama model (2023)"},{"key":"19_CR10","unstructured":"Snell, C., Klein, D., Zhong, R.: Learning by distilling context. arXiv preprint arXiv:2209.15189 (2022)"},{"key":"19_CR11","unstructured":"Xiao, G., Lin, J., Seznec, M., Wu, H., Demouth, J., Han, S.: SmoothQuant: accurate and efficient post-training quantization for large language models. In: International Conference on Machine Learning, pp. 38087\u201338099. PMLR (2023)"},{"key":"19_CR12","unstructured":"Shi, K., Sun, X., Wang, D., Fu, Y., Xu, G., Li, Q.: LLaMA-E: empowering e-commerce authoring with multi-aspect instruction following. arXiv preprint arXiv:2308.04913 (2023)"},{"key":"19_CR13","doi-asserted-by":"crossref","unstructured":"Chevalier, A., Wettig, A., Ajith, A., Chen, D.: Adapting language models to compress contexts. arXiv preprint arXiv:2305.14788 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.232"},{"key":"19_CR14","unstructured":"Yang, N., et al.: Inference with reference: lossless acceleration of large language models. arXiv preprint arXiv:2304.04487 (2023)"},{"key":"19_CR15","unstructured":"Ge, T., et al.: Extensible prompts for language models. arXiv preprint arXiv:2212.00616 (2022)"},{"key":"19_CR16","unstructured":"Goyal, S., Choudhury, A.R., Raje, S., Chakaravarthy, V., Sabharwal, Y., Verma, A.: Power-BERT: accelerating BERT inference via progressive word-vector elimination. In: International Conference on Machine Learning, pp. 3690\u20133699. PMLR (2020)"},{"key":"19_CR17","doi-asserted-by":"crossref","unstructured":"Kim, S., et al.: Learned token pruning for transformers. In: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pp. 784\u2013794 (2022)","DOI":"10.1145\/3534678.3539260"},{"key":"19_CR18","unstructured":"Rao, Y., Zhao, W., Liu, B., Lu, J., Zhou, J., Hsieh, C.J.: DynamicViT: efficient vision transformers with dynamic token sparsification. In: Advances in Neural Information Processing Systems, vol. 34, pp. 13937\u201313949 (2021)"},{"key":"19_CR19","doi-asserted-by":"crossref","unstructured":"Wingate, D., Shoeybi, M., Sorensen, T.: Prompt compression and contrastive conditioning for controllability and toxicity reduction in language models. arXiv preprint arXiv:2210.03162 (2022)","DOI":"10.18653\/v1\/2022.findings-emnlp.412"},{"key":"19_CR20","doi-asserted-by":"crossref","unstructured":"Lester, B., Al-Rfou, R., Constant, N.: The power of scale for parameter-efficient prompt tuning. arXiv preprint arXiv:2104.08691 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"19_CR21","doi-asserted-by":"crossref","unstructured":"Li, X.L., Liang, P.: Prefix-tuning: optimizing continuous prompts for generation. arXiv preprint arXiv:2101.00190 (2021)","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"19_CR22","unstructured":"Mu, J., Li, X.L., Goodman, N.: Learning to compress prompts with gist tokens. arXiv preprint arXiv:2304.08467 (2023)"},{"key":"19_CR23","doi-asserted-by":"crossref","unstructured":"Li, Y., Dong, B., Lin, C., Guerin, F.: Compressing context to enhance inference efficiency of large language models. arXiv preprint arXiv:2310.06201 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.391"},{"key":"19_CR24","doi-asserted-by":"crossref","unstructured":"Jiang, H., et al.: LongLLMlingua: accelerating and enhancing LLMs in long context scenarios via prompt compression. arXiv preprint arXiv:2310.06839 (2023)","DOI":"10.18653\/v1\/2024.acl-long.91"},{"key":"19_CR25","unstructured":"Del\u00e9tang, G., et al.: Language modeling is compression. arXiv preprint arXiv:2309.10668 (2023)"},{"key":"19_CR26","doi-asserted-by":"crossref","unstructured":"Shannon, C.E.: A mathematical theory of communication. Bell Syst. Tech. J. 27(3), 379\u2013423 (1948)","DOI":"10.1002\/j.1538-7305.1948.tb01338.x"},{"key":"19_CR27","doi-asserted-by":"crossref","unstructured":"Bunescu, R., Uduehi, O.O.: Distribution-based measures of surprise for creative language: experiments with humor and metaphor. In: Proceedings of the 3rd Workshop on Figurative Language Processing (FLP), pp. 68\u201378 (2022)","DOI":"10.18653\/v1\/2022.flp-1.10"},{"key":"19_CR28","doi-asserted-by":"crossref","unstructured":"Cilibrasi, R., Vit\u00e1nyi, P.M.: Clustering by compression. IEEE Trans. Inf. Theory 51(4), 1523\u20131545 (2005)","DOI":"10.1109\/TIT.2005.844059"},{"key":"19_CR29","unstructured":"Radford, A., et al.: Language models are unsupervised multitask learners. OpenAI blog 1(8), 9 (2019)"},{"key":"19_CR30","unstructured":"Zeng, A., et al.: GLM-130b: an open bilingual pre-trained model. arXiv preprint arXiv:2210.02414 (2022)"},{"key":"19_CR31","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: BLEU: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, pp. 311\u2013318 (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"19_CR32","unstructured":"Lin, C.Y.: Rouge: a package for automatic evaluation of summaries. In: Text Summarization Branches Out, pp. 74\u201381 (2004)"},{"key":"19_CR33","unstructured":"Zhang, T., Kishore, V., Wu, F., Weinberger, K.Q., Artzi, Y.: BERTScore: evaluating text generation with BERT. arXiv preprint arXiv:1904.09675 (2019)"},{"key":"19_CR34","unstructured":"Banerjee, S., Lavie, A.: METEOR: an automatic metric for MT evaluation with improved correlation with human judgments. In: Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization, pp. 65\u201372 (2005)"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-5663-6_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,25]],"date-time":"2024-11-25T12:07:57Z","timestamp":1732536477000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-5663-6_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819756629","9789819756636"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-5663-6_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"1 August 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tianjin","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":"5 August 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 August 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2024\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}