{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T05:18:41Z","timestamp":1784179121971,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":46,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100006374","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No.62222213, U22B2059, 62072423"],"award-info":[{"award-number":["No.62222213, U22B2059, 62072423"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006374","name":"University of Science and Technology of China","doi-asserted-by":"publisher","award":["No.YD2150002009"],"award-info":[{"award-number":["No.YD2150002009"]}],"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":[[2024,5,13]]},"DOI":"10.1145\/3589335.3648298","type":"proceedings-article","created":{"date-parts":[[2024,5,12]],"date-time":"2024-05-12T18:41:21Z","timestamp":1715539281000},"page":"20-28","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":63,"title":["Large Language Model based Long-tail Query Rewriting in Taobao Search"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2392-4946","authenticated-orcid":false,"given":"Wenjun","family":"Peng","sequence":"first","affiliation":[{"name":"University of Science and Technology of China & State Key Laboratory of Cognitive Intelligence, Hefei, Anhui, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-5685-501X","authenticated-orcid":false,"given":"Guiyang","family":"Li","sequence":"additional","affiliation":[{"name":"Taobao and Tmall Group, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5134-8900","authenticated-orcid":false,"given":"Yue","family":"Jiang","sequence":"additional","affiliation":[{"name":"Taobao and Tmall Group, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9832-5764","authenticated-orcid":false,"given":"Zilong","family":"Wang","sequence":"additional","affiliation":[{"name":"Taobao and Tmall Group, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-9838-5343","authenticated-orcid":false,"given":"Dan","family":"Ou","sequence":"additional","affiliation":[{"name":"Taobao and Tmall Group, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3742-4910","authenticated-orcid":false,"given":"Xiaoyi","family":"Zeng","sequence":"additional","affiliation":[{"name":"Taobao and Tmall Group, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3971-9907","authenticated-orcid":false,"given":"Derong","family":"Xu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China & State Key Laboratory of Cognitive Intelligence, Hefei, Anhui, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4246-5386","authenticated-orcid":false,"given":"Tong","family":"Xu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China & State Key Laboratory of Cognitive Intelligence, Hefei, Anhui, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4835-4102","authenticated-orcid":false,"given":"Enhong","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China & State Key Laboratory of Cognitive Intelligence, Hefei, Anhui, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,5,13]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"crossref","unstructured":"Sanjay Agrawal Srujana Merugu and Vivek Sembium. 2023. Enhancing ecommerce product search through reinforcement learning-powered query reformulation. In CIKM.","DOI":"10.1145\/3583780.3615474"},{"key":"e_1_3_2_2_2_1","unstructured":"Avishek Anand Abhijit Anand Vinay Setty et al. 2023. Query Understanding in the Age of Large Language Models. arXiv preprint arXiv:2306.16004 (2023)."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"crossref","unstructured":"Ioannis Antonellis Hector Garcia-Molina and Chi-Chao Chang. 2008. Simrank query rewriting through link analysis of the clickgraph (poster). In TheWebConf. 1177--1178.","DOI":"10.1145\/1367497.1367714"},{"key":"e_1_3_2_2_4_1","unstructured":"Yuntao Bai Saurav Kadavath Sandipan Kundu Amanda Askell Jackson Kernion Andy Jones Anna Chen Anna Goldie Azalia Mirhoseini Cameron McKinnon et al. 2022. Constitutional ai: Harmlessness from ai feedback. arXiv preprint arXiv:2212.08073 (2022)."},{"key":"e_1_3_2_2_5_1","volume-title":"A review of ontology based query expansion. Information processing & management 43, 4","author":"Bhogal Jagdev","year":"2007","unstructured":"Jagdev Bhogal, Andrew MacFarlane, and Peter Smith. 2007. A review of ontology based query expansion. Information processing & management 43, 4 (2007), 866--886."},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"crossref","unstructured":"Guihong Cao Jian-Yun Nie Jianfeng Gao and Stephen Robertson. 2008. Selecting good expansion terms for pseudo-relevance feedback. In SIGIR. 243--250.","DOI":"10.1145\/1390334.1390377"},{"key":"e_1_3_2_2_7_1","volume-title":"Deep reinforcement learning from human preferences. NIPS 30","author":"Christiano Paul F","year":"2017","unstructured":"Paul F Christiano, Jan Leike, Tom Brown, Miljan Martic, Shane Legg, and Dario Amodei. 2017. Deep reinforcement learning from human preferences. NIPS 30 (2017)."},{"key":"e_1_3_2_2_8_1","volume-title":"andWei-Ying Ma","author":"Cui Hang","year":"2002","unstructured":"Hang Cui, Ji-RongWen, Jian-Yun Nie, andWei-Ying Ma. 2002. Probabilistic query expansion using query logs. In TheWebConf. 325--332."},{"key":"e_1_3_2_2_9_1","volume-title":"Residual energy-based models for text generation. arXiv preprint arXiv:2004.11714","author":"Deng Yuntian","year":"2020","unstructured":"Yuntian Deng, Anton Bakhtin, Myle Ott, Arthur Szlam, and Marc'Aurelio Ranzato. 2020. Residual energy-based models for text generation. arXiv preprint arXiv:2004.11714 (2020)."},{"key":"e_1_3_2_2_10_1","volume-title":"Raft: Reward ranked finetuning for generative foundation model alignment. arXiv preprint arXiv:2304.06767","author":"Dong Hanze","year":"2023","unstructured":"Hanze Dong, Wei Xiong, Deepanshu Goyal, Rui Pan, Shizhe Diao, Jipeng Zhang, Kashun Shum, and Tong Zhang. 2023. Raft: Reward ranked finetuning for generative foundation model alignment. arXiv preprint arXiv:2304.06767 (2023)."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.26"},{"key":"e_1_3_2_2_12_1","volume-title":"Srivatsan Srinivasan, Ksenia Konyushkova, Lotte Weerts, Abhishek Sharma, Aditya Siddhant, Alex Ahern, Miaosen Wang, Chenjie Gu, et al.","author":"Gulcehre Caglar","year":"2023","unstructured":"Caglar Gulcehre, Tom Le Paine, Srivatsan Srinivasan, Ksenia Konyushkova, Lotte Weerts, Abhishek Sharma, Aditya Siddhant, Alex Ahern, Miaosen Wang, Chenjie Gu, et al. 2023. Reinforced self-training (rest) for language modeling. arXiv preprint arXiv:2308.08998 (2023)."},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"crossref","unstructured":"Jui-Ting Huang Ashish Sharma Shuying Sun Li Xia David Zhang Philip Pronin Janani Padmanabhan Giuseppe Ottaviano and Linjun Yang. 2020. Embeddingbased retrieval in facebook search. In SIGKDD. 2553--2561.","DOI":"10.1145\/3394486.3403305"},{"key":"e_1_3_2_2_14_1","unstructured":"Baichuan Inc. 2023. A large-scale 7b pretraining language model developed by baichuan-inc. https:\/\/github.com\/baichuan-inc\/Baichuan-7B"},{"key":"e_1_3_2_2_15_1","volume-title":"Query Expansion by Prompting Large Language Models. arXiv preprint arXiv:2305.03653","author":"Jagerman Rolf","year":"2023","unstructured":"Rolf Jagerman, Honglei Zhuang, Zhen Qin, Xuanhui Wang, and Michael Bendersky. 2023. Query Expansion by Prompting Large Language Models. arXiv preprint arXiv:2305.03653 (2023)."},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"crossref","unstructured":"Mu-Chu Lee Bin Gao and Ruofei Zhang. 2018. Rare query expansion through generative adversarial networks in search advertising. In SIGKDD. 500--508.","DOI":"10.1145\/3219819.3219850"},{"key":"e_1_3_2_2_17_1","volume-title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension. In ACL. 7871--7880.","author":"Lewis Mike","year":"2020","unstructured":"Mike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad, Abdelrahman Mohamed, Omer Levy, Veselin Stoyanov, and Luke Zettlemoyer. 2020. BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension. In ACL. 7871--7880."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"crossref","unstructured":"Sen Li Fuyu Lv Taiwei Jin Guiyang Li Yukun Zheng Tao Zhuang Qingwen Liu Xiaoyi Zeng James Kwok and Qianli Ma. 2022. Query Rewriting in TaoBao Search. In CIKM. 3262--3271.","DOI":"10.1145\/3511808.3557068"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"crossref","unstructured":"Sen Li Fuyu Lv Taiwei Jin Guli Lin Keping Yang Xiaoyi Zeng Xiao-Ming Wu and Qianli Ma. 2021. Embedding-based product retrieval in taobao search. In SIGKDD. 3181--3189.","DOI":"10.1145\/3447548.3467101"},{"key":"e_1_3_2_2_20_1","volume-title":"CRUD-RAG: A Comprehensive Chinese Benchmark for Retrieval-Augmented Generation of Large Language Models. arXiv preprint arXiv:2401.17043","author":"Lyu Yuanjie","year":"2024","unstructured":"Yuanjie Lyu, Zhiyu Li, Simin Niu, Feiyu Xiong, Bo Tang, Wenjin Wang, Hao Wu, Huanyong Liu, Tong Xu, and Enhong Chen. 2024. CRUD-RAG: A Comprehensive Chinese Benchmark for Retrieval-Augmented Generation of Large Language Models. arXiv preprint arXiv:2401.17043 (2024)."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"crossref","unstructured":"Saurav Manchanda Mohit Sharma and George Karypis. 2019. Intent term weighting in e-commerce queries. In CIKM. 2345--2348.","DOI":"10.1145\/3357384.3358151"},{"key":"e_1_3_2_2_22_1","unstructured":"Aritra Mandal Ishita K Khan and Prathyusha Senthil Kumar. 2019. Query Rewriting using Automatic Synonym Extraction for E-commerce Search.. In eCOM@ SIGIR."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"crossref","unstructured":"Akash Kumar Mohankumar Nikit Begwani and Amit Singh. 2021. Diversity driven query rewriting in search advertising. In SIGKDD. 3423--3431.","DOI":"10.1145\/3447548.3467202"},{"key":"e_1_3_2_2_24_1","unstructured":"Long Ouyang Jeff Wu Xu Jiang Diogo Almeida Carroll L Wainwright Pamela Mishkin Chong Zhang Sandhini Agarwal Katarina Slama Alex Ray et al. 2022. Training language models to follow instructions with human feedback 2022. arXiv preprint arXiv:2203.02155 13 (2022)."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-40292-0_13"},{"key":"e_1_3_2_2_26_1","volume-title":"Query Rewriting via Cycle-Consistent Translation for E-Commerce Search","author":"Qiu Yiming","unstructured":"Yiming Qiu, Kang Zhang, Han Zhang, Songlin Wang, Sulong Xu, Yun Xiao, Bo Long, and Wen-Yun Yang. 2021. Query Rewriting via Cycle-Consistent Translation for E-Commerce Search. In ICDE. IEEE, 2435--2446."},{"key":"e_1_3_2_2_27_1","volume-title":"Direct preference optimization: Your language model is secretly a reward model. arXiv preprint arXiv:2305.18290","author":"Rafailov Rafael","year":"2023","unstructured":"Rafael Rafailov, Archit Sharma, Eric Mitchell, Stefano Ermon, Christopher D Manning, and Chelsea Finn. 2023. Direct preference optimization: Your language model is secretly a reward model. arXiv preprint arXiv:2305.18290 (2023)."},{"key":"e_1_3_2_2_28_1","volume-title":"Preference ranking optimization for human alignment. arXiv preprint arXiv:2306.17492","author":"Song Feifan","year":"2023","unstructured":"Feifan Song, Bowen Yu, Minghao Li, Haiyang Yu, Fei Huang, Yongbin Li, and Houfeng Wang. 2023. Preference ranking optimization for human alignment. arXiv preprint arXiv:2306.17492 (2023)."},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"crossref","unstructured":"Zhenqiao Song Jiaze Chen Hao Zhou and Lei Li. 2021. Triangular Bidword Generation for Sponsored Search Auction. In WSDM. 707--715.","DOI":"10.1145\/3437963.3441819"},{"key":"e_1_3_2_2_30_1","first-page":"3008","article-title":"Learning to summarize with human feedback","volume":"33","author":"Stiennon Nisan","year":"2020","unstructured":"Nisan Stiennon, Long Ouyang, Jeffrey Wu, Daniel Ziegler, Ryan Lowe, Chelsea Voss, Alec Radford, Dario Amodei, and Paul F Christiano. 2020. Learning to summarize with human feedback. NIPS 33 (2020), 3008--3021.","journal-title":"NIPS"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"crossref","unstructured":"Tao Tao and ChengXiang Zhai. 2006. Regularized estimation of mixture models for robust pseudo-relevance feedback. In SIGIR. 162--169.","DOI":"10.1145\/1148170.1148201"},{"key":"e_1_3_2_2_32_1","unstructured":"Qwen Team. 2023. QWEN TECHNICAL REPORT. Technical Report. Alibaba Group. https:\/\/qianwen-res.oss-cn-beijing.aliyuncs.com\/QWEN_TECHNICAL_ REPORT.pdf"},{"key":"e_1_3_2_2_33_1","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale et al. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)."},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"crossref","unstructured":"BinbinWang Mingming Li Zhixiong Zeng Jingwei Zhuo SonglinWang Sulong Xu Bo Long and Weipeng Yan. 2023. Learning Multi-Stage Multi-Grained Semantic Embeddings for E-Commerce Search. In TheWebConf. 411--415.","DOI":"10.1145\/3543873.3584638"},{"key":"e_1_3_2_2_35_1","unstructured":"Cunxiang Wang Xiaoze Liu Yuanhao Yue Xiangru Tang Tianhang Zhang Cheng Jiayang Yunzhi Yao Wenyang Gao Xuming Hu Zehan Qi et al. 2023. Survey on factuality in large language models: Knowledge retrieval and domain-specificity. arXiv preprint arXiv:2310.07521 (2023)."},{"key":"e_1_3_2_2_36_1","volume-title":"Query2doc: Query Expansion with Large Language Models. arXiv preprint arXiv:2303.07678","author":"Wang Liang","year":"2023","unstructured":"Liang Wang, Nan Yang, and Furu Wei. 2023. Query2doc: Query Expansion with Large Language Models. arXiv preprint arXiv:2303.07678 (2023)."},{"key":"e_1_3_2_2_37_1","volume-title":"Can ChatGPT write a good boolean query for systematic review literature search? arXiv preprint arXiv:2302.03495","author":"Wang Shuai","year":"2023","unstructured":"Shuai Wang, Harrisen Scells, Bevan Koopman, and Guido Zuccon. 2023. Can ChatGPT write a good boolean query for systematic review literature search? arXiv preprint arXiv:2302.03495 (2023)."},{"key":"e_1_3_2_2_38_1","volume-title":"QUEEN: Neural query rewriting in e-commerce.","author":"Wang Yaxuan","year":"2021","unstructured":"Yaxuan Wang, Hanqing Lu, Yunwen Xu, Rahul Goutam, Yiwei Song, and Bing Yin. 2021. QUEEN: Neural query rewriting in e-commerce. (2021)."},{"key":"e_1_3_2_2_39_1","volume-title":"Large Language Models for Generative Information Extraction: A Survey. arXiv preprint arXiv:2312.17617","author":"Xu Derong","year":"2023","unstructured":"Derong Xu, Wei Chen, Wenjun Peng, Chao Zhang, Tong Xu, Xiangyu Zhao, Xian Wu, Yefeng Zheng, and Enhong Chen. 2023. Large Language Models for Generative Information Extraction: A Survey. arXiv preprint arXiv:2312.17617 (2023)."},{"key":"e_1_3_2_2_40_1","volume-title":"Acm sigir forum","author":"Xu Jinxi","unstructured":"Jinxi Xu and W Bruce Croft. 2017. Quary expansion using local and global document analysis. In Acm sigir forum, Vol. 51. ACM New York, NY, USA, 168--175."},{"key":"e_1_3_2_2_41_1","unstructured":"Aiyuan Yang Bin Xiao Bingning Wang Borong Zhang Chao Yin Chenxu Lv Da Pan Dian Wang Dong Yan Fan Yang et al. 2023. Baichuan 2: Open Large-scale Language Models. arXiv preprint arXiv:2309.10305 (2023)."},{"key":"e_1_3_2_2_42_1","volume-title":"Rrhf: Rank responses to align language models with human feedback without tears. arXiv preprint arXiv:2304.05302","author":"Yuan Zheng","year":"2023","unstructured":"Zheng Yuan, Hongyi Yuan, Chuanqi Tan, Wei Wang, Songfang Huang, and Fei Huang. 2023. Rrhf: Rank responses to align language models with human feedback without tears. arXiv preprint arXiv:2304.05302 (2023)."},{"key":"e_1_3_2_2_43_1","unstructured":"Aohan Zeng Xiao Liu Zhengxiao Du Zihan Wang Hanyu Lai Ming Ding Zhuoyi Yang Yifan Xu Wendi Zheng Xiao Xia et al. 2022. Glm-130b: An open bilingual pre-trained model. arXiv preprint arXiv:2210.02414 (2022)."},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"crossref","unstructured":"Han Zhang Songlin Wang Kang Zhang Zhiling Tang Yunjiang Jiang Yun Xiao Weipeng Yan and Wen-Yun Yang. 2020. Towards personalized and semantic retrieval: An end-to-end solution for e-commerce search via embedding learning. In SIGIR. 2407--2416.","DOI":"10.1145\/3397271.3401446"},{"key":"e_1_3_2_2_45_1","unstructured":"Yue Zhang Yafu Li Leyang Cui Deng Cai Lemao Liu Tingchen Fu Xinting Huang Enbo Zhao Yu Zhang Yulong Chen et al. 2023. Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models. arXiv preprint arXiv:2309.01219 (2023)."},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"crossref","unstructured":"Zhi Zheng Kai Hui Ben He Xianpei Han Le Sun and Andrew Yates. 2020. BERT-QE: Contextualized Query Expansion for Document Re-ranking. In EMNLP. 4718--4728.","DOI":"10.18653\/v1\/2020.findings-emnlp.424"}],"event":{"name":"WWW '24: The ACM Web Conference 2024","location":"Singapore Singapore","acronym":"WWW '24","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Companion Proceedings of the ACM Web Conference 2024"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3589335.3648298","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3589335.3648298","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:33:05Z","timestamp":1755822785000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3589335.3648298"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":46,"alternative-id":["10.1145\/3589335.3648298","10.1145\/3589335"],"URL":"https:\/\/doi.org\/10.1145\/3589335.3648298","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]},"assertion":[{"value":"2024-05-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}