{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T15:32:22Z","timestamp":1783611142234,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":39,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,10]]},"DOI":"10.1145\/3746252.3761549","type":"proceedings-article","created":{"date-parts":[[2025,11,8]],"date-time":"2025-11-08T01:03:42Z","timestamp":1762563822000},"page":"6185-6192","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Leveraging Generative Models for Real-Time Query-Driven Text Summarization in Large-Scale Web Search"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-1802-2592","authenticated-orcid":false,"given":"Zeyu","family":"Xiong","sequence":"first","affiliation":[{"name":"Baidu Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-6528-1771","authenticated-orcid":false,"given":"Yixuan","family":"Nan","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-9054-3322","authenticated-orcid":false,"given":"Li","family":"Gao","sequence":"additional","affiliation":[{"name":"Baidu Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-0568-5658","authenticated-orcid":false,"given":"Hengzhu","family":"Tang","sequence":"additional","affiliation":[{"name":"Baidu Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9212-1947","authenticated-orcid":false,"given":"Shuaiqiang","family":"Wang","sequence":"additional","affiliation":[{"name":"Baidu Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-7347-143X","authenticated-orcid":false,"given":"Junfeng","family":"Wang","sequence":"additional","affiliation":[{"name":"Baidu Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0684-6205","authenticated-orcid":false,"given":"Dawei","family":"Yin","sequence":"additional","affiliation":[{"name":"Baidu Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,11,10]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICWR.2018.8387248"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/2590972"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/0306-4573(95)00052-I"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICICT46931.2019.8977708"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.3115\/1654679.1654689"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6266"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.5555\/1622487.1622501"},{"key":"e_1_3_2_1_8_1","volume-title":"Break the sequential dependency of llm inference using lookahead decoding. arXiv preprint arXiv:2402.02057","author":"Fu Yichao","year":"2024","unstructured":"Yichao Fu, Peter Bailis, Ion Stoica, and Hao Zhang. 2024. Break the sequential dependency of llm inference using lookahead decoding. arXiv preprint arXiv:2402.02057 (2024)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.3390\/app13137620"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2025.104104"},{"key":"e_1_3_2_1_11_1","unstructured":"Aaron Grattafiori Abhimanyu Dubey Abhinav Jauhri Abhinav Pandey Abhishek Kadian Ahmad Al-Dahle Aiesha Letman Akhil Mathur Alan Schelten Alex Vaughan et al. 2024. The llama 3 herd of models. arXiv preprint arXiv:2407.21783 (2024)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.735"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.118442"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/IS.2004.1344634"},{"key":"e_1_3_2_1_15_1","volume-title":"Scaling laws for neural language models. arXiv preprint arXiv:2001.08361","author":"Kaplan Jared","year":"2020","unstructured":"Jared Kaplan, Sam McCandlish, Tom Henighan, Tom B Brown, Benjamin Chess, Rewon Child, Scott Gray, Alec Radford, Jeffrey Wu, and Dario Amodei. 2020. Scaling laws for neural language models. arXiv preprint arXiv:2001.08361 (2020)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"e_1_3_2_1_17_1","volume-title":"Proactive Guidance of Multi-Turn Conversation in Industrial Search. arXiv preprint arXiv:2505.24251","author":"Li Xiaoyu","year":"2025","unstructured":"Xiaoyu Li, Xiao Li, Li Gao, Yiding Liu, Xiaoyang Wang, Shuaiqiang Wang, Junfeng Wang, and Dawei Yin. 2025. Proactive Guidance of Multi-Turn Conversation in Industrial Search. arXiv preprint arXiv:2505.24251 (2025)."},{"key":"e_1_3_2_1_18_1","volume-title":"Rouge: A package for automatic evaluation of summaries. In Text summarization branches out. 74-81.","author":"Lin Chin-Yew","year":"2004","unstructured":"Chin-Yew Lin. 2004. Rouge: A package for automatic evaluation of summaries. In Text summarization branches out. 74-81."},{"key":"e_1_3_2_1_19_1","volume-title":"The automatic creation of literature abstracts. IBM Journal of research and development","author":"Luhn Hans Peter","year":"1958","unstructured":"Hans Peter Luhn. 1958. The automatic creation of literature abstracts. IBM Journal of research and development, Vol. 2, 2 (1958), 159-165."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2013.02.015"},{"key":"e_1_3_2_1_21_1","unstructured":"Paulius Micikevicius Dusan Stosic Neil Burgess Marius Cornea Pradeep Dubey Richard Grisenthwaite Sangwon Ha Alexander Heinecke Patrick Judd John Kamalu et al. 2022. Fp8 formats for deep learning. arXiv preprint arXiv:2209.05433 (2022)."},{"key":"e_1_3_2_1_22_1","volume-title":"Proceedings of the 2004 conference on empirical methods in natural language processing. 404-411","author":"Mihalcea Rada","year":"2004","unstructured":"Rada Mihalcea and Paul Tarau. 2004. Textrank: Bringing order into text. In Proceedings of the 2004 conference on empirical methods in natural language processing. 404-411."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1111\/exsy.13462"},{"key":"e_1_3_2_1_24_1","first-page":"80","article-title":"Similarity-based query-focused multi-document summarization using crowdsourced and manually-built lexical-semantic resources. In 2015 IEEE Trustcom\/BigDataSE\/ISPA, Vol. 2","author":"Mohamed Muhidin A","year":"2015","unstructured":"Muhidin A Mohamed and Mourad Oussalah. 2015. Similarity-based query-focused multi-document summarization using crowdsourced and manually-built lexical-semantic resources. In 2015 IEEE Trustcom\/BigDataSE\/ISPA, Vol. 2. IEEE, 80-87.","journal-title":"IEEE"},{"key":"e_1_3_2_1_25_1","volume-title":"Diversity driven attention model for query-based abstractive summarization. arXiv preprint arXiv:1704.08300","author":"Nema Preksha","year":"2017","unstructured":"Preksha Nema, Mitesh Khapra, Anirban Laha, and Balaraman Ravindran. 2017. Diversity driven attention model for query-based abstractive summarization. arXiv preprint arXiv:1704.08300 (2017)."},{"key":"e_1_3_2_1_26_1","unstructured":"NVIDIA Corporation. 2025. TensorRT-LLM: Large Language Model Inference Library by NVIDIA. https:\/\/github.com\/NVIDIA\/TensorRT-LLM. Accessed: 2025-04-05."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jksuci.2024.102178"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531901"},{"key":"e_1_3_2_1_29_1","volume-title":"High quality information extraction and query-oriented summarization for automatic query-reply in social network. Expert Systems with applications","author":"Peng Min","year":"2016","unstructured":"Min Peng, Binlong Gao, Jiahui Zhu, Jiajia Huang, Mengting Yuan, and Fei Li. 2016. High quality information extraction and query-oriented summarization for automatic query-reply in social network. Expert Systems with applications, Vol. 44 (2016), 92-101."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i23.34691"},{"key":"e_1_3_2_1_31_1","unstructured":"Alec Radford Jeffrey Wu Rewon Child David Luan Dario Amodei Ilya Sutskever et al. 2019. Language models are unsupervised multitask learners. OpenAI blog Vol. 1 8 (2019) 9."},{"key":"e_1_3_2_1_32_1","first-page":"53728","article-title":"Direct preference optimization: Your language model is secretly a reward model","volume":"36","author":"Rafailov Rafael","year":"2023","unstructured":"Rafael Rafailov, Archit Sharma, Eric Mitchell, Christopher D Manning, Stefano Ermon, and Chelsea Finn. 2023. Direct preference optimization: Your language model is secretly a reward model. Advances in Neural Information Processing Systems, Vol. 36 (2023), 53728-53741.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISACC.2015.7377323"},{"key":"e_1_3_2_1_34_1","volume-title":"Qontsum: On contrasting salient content for query-focused summarization. arXiv preprint arXiv:2307.07586","author":"Sotudeh Sajad","year":"2023","unstructured":"Sajad Sotudeh and Nazli Goharian. 2023. Qontsum: On contrasting salient content for query-focused summarization. arXiv preprint arXiv:2307.07586 (2023)."},{"key":"e_1_3_2_1_35_1","unstructured":"Yu Sun Shuohuan Wang Shikun Feng Siyu Ding Chao Pang Junyuan Shang Jiaxiang Liu Xuyi Chen Yanbin Zhao Yuxiang Lu et al. 2021. Ernie 3.0: Large-scale knowledge enhanced pre-training for language understanding and generation. arXiv preprint arXiv:2107.02137 (2021)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/1277741.1277766"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591936"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-017-1042-4"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2024.108148"}],"event":{"name":"CIKM '25: The 34th ACM International Conference on Information and Knowledge Management","location":"Seoul Republic of Korea","acronym":"CIKM '25","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the 34th ACM International Conference on Information and Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746252.3761549","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T01:16:48Z","timestamp":1765502208000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746252.3761549"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,10]]},"references-count":39,"alternative-id":["10.1145\/3746252.3761549","10.1145\/3746252"],"URL":"https:\/\/doi.org\/10.1145\/3746252.3761549","relation":{},"subject":[],"published":{"date-parts":[[2025,11,10]]},"assertion":[{"value":"2025-11-10","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}