{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T19:10:05Z","timestamp":1755889805269,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":65,"publisher":"ACM","funder":[{"name":"National Key R&D Program of China","award":["2022ZD0114804"],"award-info":[{"award-number":["2022ZD0114804"]}]},{"name":"Shanghai Municipal Science and Technology Major Project","award":["2021SHZDZX0102"],"award-info":[{"award-number":["2021SHZDZX0102"]}]},{"DOI":"10.13039\/501100006374","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["624B2096, 62322603, 62177033"],"award-info":[{"award-number":["624B2096, 62322603, 62177033"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,7,13]]},"DOI":"10.1145\/3726302.3729961","type":"proceedings-article","created":{"date-parts":[[2025,7,14]],"date-time":"2025-07-14T14:55:26Z","timestamp":1752504926000},"page":"1891-1901","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Efficiency Unleashed: Inference Acceleration for LLM-based Recommender Systems with Speculative Decoding"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6883-881X","authenticated-orcid":false,"given":"Yunjia","family":"Xi","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0410-5426","authenticated-orcid":false,"given":"Hangyu","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3750-2533","authenticated-orcid":false,"given":"Bo","family":"Chen","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8953-3203","authenticated-orcid":false,"given":"Jianghao","family":"Lin","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8567-2185","authenticated-orcid":false,"given":"Menghui","family":"Zhu","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9148-3997","authenticated-orcid":false,"given":"Weiwen","family":"Liu","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9224-2431","authenticated-orcid":false,"given":"Ruiming","family":"Tang","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3620-5086","authenticated-orcid":false,"given":"Zhewei","family":"Wei","sequence":"additional","affiliation":[{"name":"Renmin University of China, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0127-2425","authenticated-orcid":false,"given":"Weinan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0281-8271","authenticated-orcid":false,"given":"Yong","family":"Yu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]}],"member":"320","published-online":{"date-parts":[[2025,7,13]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2020. MindSpore. https:\/\/www.mindspore.cn\/"},{"key":"e_1_3_2_1_2_1","unstructured":"Jinze Bai Shuai Bai Yunfei Chu Zeyu Cui Kai Dang Xiaodong Deng Yang Fan Wenbin Ge Yu Han Fei Huang et al. 2023. Qwen technical report. arXiv preprint arXiv:2309.16609 (2023)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3604915.3608857"},{"key":"e_1_3_2_1_4_1","volume-title":"Product Attribute Value Extraction using Large Language Models. arXiv preprint arXiv:2310.12537","author":"Brinkmann Alexander","year":"2023","unstructured":"Alexander Brinkmann, Roee Shraga, and Christian Bizer. 2023. Product Attribute Value Extraction using Large Language Models. arXiv preprint arXiv:2310.12537 (2023)."},{"key":"e_1_3_2_1_5_1","volume-title":"Yuanzhi Li, Scott Lundberg, et al.","author":"Bubeck S\u00e9bastien","year":"2023","unstructured":"S\u00e9bastien Bubeck, Varun Chandrasekaran, Ronen Eldan, Johannes Gehrke, Eric Horvitz, Ece Kamar, Peter Lee, Yin Tat Lee, Yuanzhi Li, Scott Lundberg, et al. 2023. Sparks of arti#cial general intelligence: Early experiments with gpt-4. arXiv preprint arXiv:2303.12712 (2023)."},{"key":"e_1_3_2_1_6_1","volume-title":"Medusa: Simple llm inference acceleration framework with multiple decoding heads. arXiv preprint arXiv:2401.10774","author":"Cai Tianle","year":"2024","unstructured":"Tianle Cai, Yuhong Li, Zhengyang Geng, Hongwu Peng, Jason D Lee, Deming Chen, and Tri Dao. 2024. Medusa: Simple llm inference acceleration framework with multiple decoding heads. arXiv preprint arXiv:2401.10774 (2024)."},{"key":"e_1_3_2_1_7_1","volume-title":"Accelerating large language model decoding with speculative sampling. arXiv preprint arXiv:2302.01318","author":"Chen Charlie","year":"2023","unstructured":"Charlie Chen, Sebastian Borgeaud, Geottrey Irving, Jean-Baptiste Lespiau, Laurent Sifre, and John Jumper. 2023. Accelerating large language model decoding with speculative sampling. arXiv preprint arXiv:2302.01318 (2023)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"crossref","unstructured":"Jin Chen Zheng Liu Xu Huang Chenwang Wu Qi Liu Gangwei Jiang Yuanhao Pu Yuxuan Lei Xiaolong Chen XingmeiWang et al. 2023. When large language models meet personalization: Perspectives of challenges and opportunities. arXiv preprint arXiv:2307.16376 (2023).","DOI":"10.1007\/s11280-024-01276-1"},{"key":"e_1_3_2_1_9_1","volume-title":"Uncovering ChatGPT's Capabilities in Recommender Systems. arXiv preprint arXiv:2305.02182","author":"Dai Sunhao","year":"2023","unstructured":"Sunhao Dai, Ninglu Shao, Haiyuan Zhao, Weijie Yu, Zihua Si, Chen Xu, Zhongxiang Sun, Xiao Zhang, and Jun Xu. 2023. Uncovering ChatGPT's Capabilities in Recommender Systems. arXiv preprint arXiv:2305.02182 (2023)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/1457838.1457895"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657689"},{"key":"e_1_3_2_1_12_1","volume-title":"DisCo: Towards Harmonious Disentanglement and Collaboration between Tabular and Semantic Space for Recommendation. arXiv preprint arXiv:2406.00011","author":"Du Kounianhua","year":"2024","unstructured":"Kounianhua Du, Jizheng Chen, Jianghao Lin, Yunjia Xi, HangyuWang, Xinyi Dai, Bo Chen, Ruiming Tang, and Weinan Zhang. 2024. DisCo: Towards Harmonious Disentanglement and Collaboration between Tabular and Semantic Space for Recommendation. arXiv preprint arXiv:2406.00011 (2024)."},{"key":"e_1_3_2_1_13_1","volume-title":"Recommender systems in the era of large language models (llms). arXiv preprint arXiv:2307.02046","author":"Fan Wenqi","year":"2023","unstructured":"Wenqi Fan, Zihuai Zhao, Jiatong Li, Yunqing Liu, Xiaowei Mei, YiqiWang, Jiliang Tang, and Qing Li. 2023. Recommender systems in the era of large language models (llms). arXiv preprint arXiv:2307.02046 (2023)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3661357"},{"key":"e_1_3_2_1_15_1","unstructured":"Yichao Fu Peter Bailis Ion Stoica and Hao Zhang. 2024. Break the Sequential Dependency of LLM Inference Using Lookahead Decoding. In Forty-#rst International Conference on Machine Learning."},{"key":"e_1_3_2_1_16_1","volume-title":"Chat-REC: Towards Interactive and Explainable LLMs-Augmented Recommender System. arXiv preprint arXiv:2303.14524","author":"Gao Yunfan","year":"2023","unstructured":"Yunfan Gao, Tao Sheng, Youlin Xiang, Yun Xiong, Haofen Wang, and Jiawei Zhang. 2023. Chat-REC: Towards Interactive and Explainable LLMs-Augmented Recommender System. arXiv preprint arXiv:2303.14524 (2023)."},{"key":"e_1_3_2_1_17_1","volume-title":"Chatglm: A family of large language models from glm-130b to glm-4 all tools. arXiv preprint arXiv:2406.12793","author":"Aohan Zeng Team GLM","year":"2024","unstructured":"Team GLM, Aohan Zeng, Bin Xu, Bowen Wang, Chenhui Zhang, Da Yin, Dan Zhang, Diego Rojas, Guanyu Feng, Hanlin Zhao, et al. 2024. Chatglm: A family of large language models from glm-130b to glm-4 all tools. arXiv preprint arXiv:2406.12793 (2024)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401063"},{"key":"e_1_3_2_1_19_1","volume-title":"Rest: Retrieval-based speculative decoding. arXiv preprint arXiv:2311.08252","author":"He Zhenyu","year":"2023","unstructured":"Zhenyu He, Zexuan Zhong, Tianle Cai, Jason D Lee, and Di He. 2023. Rest: Retrieval-based speculative decoding. arXiv preprint arXiv:2311.08252 (2023)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-56060-6_24"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-022-1250-2"},{"key":"e_1_3_2_1_22_1","volume-title":"Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lucile Saulnier, et al.","author":"Jiang Albert Q","year":"2023","unstructured":"Albert Q Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lucile Saulnier, et al. 2023. Mistral 7B. arXiv preprint arXiv:2310.06825 (2023)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/3477.764879"},{"key":"e_1_3_2_1_24_1","volume-title":"International Conference on Machine Learning. PMLR","author":"Leviathan Yaniv","year":"2023","unstructured":"Yaniv Leviathan, Matan Kalman, and Yossi Matias. 2023. Fast inference from transformers via speculative decoding. In International Conference on Machine Learning. PMLR, 19274-19286."},{"key":"e_1_3_2_1_25_1","volume-title":"TagGPT: Large Language Models are Zero-shot Multimodal Taggers. arXiv preprint arXiv:2304.03022","author":"Li Chen","year":"2023","unstructured":"Chen Li, Yixiao Ge, Jiayong Mao, Dian Li, and Ying Shan. 2023. TagGPT: Large Language Models are Zero-shot Multimodal Taggers. arXiv preprint arXiv:2304.03022 (2023)."},{"key":"e_1_3_2_1_26_1","volume-title":"Large Language Models for Generative Recommendation: A Survey and Visionary Discussions. arXiv preprint arXiv:2309.01157","author":"Li Lei","year":"2023","unstructured":"Lei Li, Yongfeng Zhang, Dugang Liu, and Li Chen. 2023. Large Language Models for Generative Recommendation: A Survey and Visionary Discussions. arXiv preprint arXiv:2309.01157 (2023)."},{"key":"e_1_3_2_1_27_1","volume-title":"Eagle: Speculative sampling requires rethinking feature uncertainty. arXiv preprint arXiv:2401.15077","author":"Li Yuhui","year":"2024","unstructured":"Yuhui Li, Fangyun Wei, Chao Zhang, and Hongyang Zhang. 2024. Eagle: Speculative sampling requires rethinking feature uncertainty. arXiv preprint arXiv:2401.15077 (2024)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645396"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-024-40039-z"},{"key":"e_1_3_2_1_30_1","unstructured":"Jianghao Lin Xinyi Dai Yunjia Xi Weiwen Liu Bo Chen Xiangyang Li Chenxu Zhu Huifeng Guo Yong Yu Ruiming Tang et al. 2023. How Can Recommender Systems Bene#t from Large Language Models: A Survey. arXiv preprint arXiv:2306.05817 (2023)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645467"},{"key":"e_1_3_2_1_32_1","volume-title":"Is ChatGPT a Good Recommender? A Preliminary Study. arXiv preprint arXiv:2304.10149","author":"Liu Junling","year":"2023","unstructured":"Junling Liu, Chao Liu, Renjie Lv, Kang Zhou, and Yan Zhang. 2023. Is ChatGPT a Good Recommender? A Preliminary Study. arXiv preprint arXiv:2304.10149 (2023)."},{"key":"e_1_3_2_1_33_1","volume-title":"prompt and recommendation: A comprehensive survey of language modelling paradigm adaptations in recommender systems. arXiv preprint arXiv:2302.03735","author":"Liu Peng","year":"2023","unstructured":"Peng Liu, Lemei Zhang, and Jon Atle Gulla. 2023. Pre-train, prompt and recommendation: A comprehensive survey of language modelling paradigm adaptations in recommender systems. arXiv preprint arXiv:2302.03735 (2023)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3616855.3635845"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589335.3648305"},{"key":"e_1_3_2_1_36_1","volume-title":"KELLMRec: Knowledge-Enhanced Large Language Models for Recommendation. arXiv preprint arXiv:2403.06642","author":"Luo Weiqing","year":"2024","unstructured":"Weiqing Luo, Chonggang Song, Lingling Yi, and Gong Cheng. 2024. KELLMRec: Knowledge-Enhanced Large Language Models for Recommendation. arXiv preprint arXiv:2403.06642 (2024)."},{"key":"e_1_3_2_1_37_1","volume-title":"Llmrec: Personalized recommendation via prompting large language models. arXiv preprint arXiv:2307.15780","author":"Lyu Hanjia","year":"2023","unstructured":"Hanjia Lyu, Song Jiang, Hanqing Zeng, Yinglong Xia, and Jiebo Luo. 2023. Llmrec: Personalized recommendation via prompting large language models. arXiv preprint arXiv:2307.15780 (2023)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651335"},{"key":"e_1_3_2_1_39_1","unstructured":"OpenAI. 2023. GPT-4 Technical Report. CoRR abs\/2303.08774 (2023). https:\/\/doi.org\/10.48550\/arXiv.2303.08774"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645458"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657782"},{"key":"e_1_3_2_1_42_1","volume-title":"Accelerating transformer inference for translation via parallel decoding. arXiv preprint arXiv:2305.10427","author":"Santilli Andrea","year":"2023","unstructured":"Andrea Santilli, Silvio Severino, Emilian Postolache, Valentino Maiorca, Michele Mancusi, Riccardo Marin, and Emanuele Rodol\u00e0. 2023. Accelerating transformer inference for translation via parallel decoding. arXiv preprint arXiv:2305.10427 (2023)."},{"key":"e_1_3_2_1_43_1","volume-title":"Blockwise parallel decoding for deep autoregressive models. Advances in Neural Information Processing Systems 31","author":"Stern Mitchell","year":"2018","unstructured":"Mitchell Stern, Noam Shazeer, and Jakob Uszkoreit. 2018. Blockwise parallel decoding for deep autoregressive models. Advances in Neural Information Processing Systems 31 (2018)."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657821"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3640457.3688131"},{"key":"e_1_3_2_1_46_1","volume-title":"FLIP: Towards Fine-grained Alignment between ID-based Models and Pretrained Language Models for CTR Prediction. arXiv e-prints","author":"Wang Hangyu","year":"2023","unstructured":"Hangyu Wang, Jianghao Lin, Xiangyang Li, Bo Chen, Chenxu Zhu, Ruiming Tang, Weinan Zhang, and Yong Yu. 2023. FLIP: Towards Fine-grained Alignment between ID-based Models and Pretrained Language Models for CTR Prediction. arXiv e-prints (2023), arXiv-2310."},{"key":"e_1_3_2_1_47_1","first-page":"1785","volume-title":"Proceedings of the Web Conference","author":"Shivanna Rakesh","year":"2021","unstructured":"RuoxiWang, Rakesh Shivanna, Derek Cheng, Sagar Jain, Dong Lin, Lichan Hong, and Ed Chi. 2021. DCN V2: Improved Deep & Cross Network and Practical Lessons for Web-Scale Learning to Rank Systems. In Proceedings of the Web Conference 2021. 1785-1797."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645671"},{"key":"e_1_3_2_1_49_1","unstructured":"Likang Wu Zhi Zheng Zhaopeng Qiu Hao Wang Hongchao Gu Tingjia Shen Chuan Qin Chen Zhu Hengshu Zhu Qi Liu et al. 2023. A Survey on Large Language Models for Recommendation. arXiv preprint arXiv:2305.19860 (2023)."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3640457.3688104"},{"key":"e_1_3_2_1_51_1","volume-title":"MemoCRS: Memory-enhanced Sequential Conversational Recommender Systems with Large Language Models. arXiv preprint arXiv:2407.04960","author":"Xi Yunjia","year":"2024","unstructured":"Yunjia Xi,Weiwen Liu, Jianghao Lin, Bo Chen, Ruiming Tang,Weinan Zhang, and Yong Yu. 2024. MemoCRS: Memory-enhanced Sequential Conversational Recommender Systems with Large Language Models. arXiv preprint arXiv:2407.04960 (2024)."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599878"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.257"},{"key":"e_1_3_2_1_54_1","volume-title":"Unlocking e#ciency in large language model inference: A comprehensive survey of speculative decoding. arXiv preprint arXiv:2401.07851","author":"Xia Heming","year":"2024","unstructured":"Heming Xia, Zhe Yang, Qingxiu Dong, Peiyi Wang, Yongqi Li, Tao Ge, Tianyu Liu, Wenjie Li, and Zhifang Sui. 2024. Unlocking e#ciency in large language model inference: A comprehensive survey of speculative decoding. arXiv preprint arXiv:2401.07851 (2024)."},{"key":"e_1_3_2_1_55_1","volume-title":"Predictive pipelined decoding: A compute-latency trade-ott for exact LLM decoding. arXiv preprint arXiv:2307.05908","author":"Yang Seongjun","year":"2023","unstructured":"Seongjun Yang, Gibbeum Lee, Jaewoong Cho, Dimitris Papailiopoulos, and Kangwook Lee. 2023. Predictive pipelined decoding: A compute-latency trade-ott for exact LLM decoding. arXiv preprint arXiv:2307.05908 (2023)."},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3282907"},{"key":"e_1_3_2_1_57_1","volume-title":"Collm: Integrating collaborative embeddings into large language models for recommendation. arXiv preprint arXiv:2310.19488","author":"Zhang Yang","year":"2023","unstructured":"Yang Zhang, Fuli Feng, Jizhi Zhang, Keqin Bao, Qifan Wang, and Xiangnan He. 2023. Collm: Integrating collaborative embeddings into large language models for recommendation. arXiv preprint arXiv:2310.19488 (2023)."},{"key":"e_1_3_2_1_58_1","unstructured":"Wayne Xin Zhao Kun Zhou Junyi Li Tianyi Tang Xiaolei Wang Yupeng Hou Yingqian Min Beichen Zhang Junjie Zhang Zican Dong et al. 2023. A survey of large language models. arXiv preprint arXiv:2303.18223 (2023)."},{"key":"e_1_3_2_1_59_1","volume-title":"Lookahead: An inference acceleration framework for large language model with lossless generation accuracy. arXiv preprint arXiv:2312.12728","author":"Zhao Yao","year":"2023","unstructured":"Yao Zhao, Zhitian Xie, Chenyi Zhuang, and Jinjie Gu. 2023. Lookahead: An inference acceleration framework for large language model with lossless generation accuracy. arXiv preprint arXiv:2312.12728 (2023)."},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE60146.2024.00118"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645358"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219823"},{"key":"e_1_3_2_1_63_1","volume-title":"Aditya Krishna Menon, Afshin Rostamizadeh, Sanjiv Kumar, Jean-Fran\u00e7ois Kagy, and Rishabh Agarwal.","author":"Zhou Yongchao","year":"2023","unstructured":"Yongchao Zhou, Kaifeng Lyu, Ankit Singh Rawat, Aditya Krishna Menon, Afshin Rostamizadeh, Sanjiv Kumar, Jean-Fran\u00e7ois Kagy, and Rishabh Agarwal. 2023. Distillspec: Improving speculative decoding via knowledge distillation. arXiv preprint arXiv:2310.08461 (2023)."},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645347"},{"key":"e_1_3_2_1_65_1","volume-title":"Large language models for information retrieval: A survey. arXiv preprint arXiv:2308.07107","author":"Zhu Yutao","year":"2023","unstructured":"Yutao Zhu, Huaying Yuan, Shuting Wang, Jiongnan Liu, Wenhan Liu, Chenlong Deng, Zhicheng Dou, and Ji-Rong Wen. 2023. Large language models for information retrieval: A survey. arXiv preprint arXiv:2308.07107 (2023)."}],"event":{"name":"SIGIR '25: The 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"],"location":"Padua Italy","acronym":"SIGIR '25"},"container-title":["Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3726302.3729961","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T18:34:13Z","timestamp":1755887653000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3726302.3729961"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,13]]},"references-count":65,"alternative-id":["10.1145\/3726302.3729961","10.1145\/3726302"],"URL":"https:\/\/doi.org\/10.1145\/3726302.3729961","relation":{},"subject":[],"published":{"date-parts":[[2025,7,13]]},"assertion":[{"value":"2025-07-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}