{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T16:33:51Z","timestamp":1773246831307,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":35,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,8,3]]},"DOI":"10.1145\/3711896.3737242","type":"proceedings-article","created":{"date-parts":[[2025,8,3]],"date-time":"2025-08-03T21:07:39Z","timestamp":1754255259000},"page":"4882-4890","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["LLM4Tag: Automatic Tagging System for Information Retrieval via Large Language Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9224-2431","authenticated-orcid":false,"given":"Ruiming","family":"Tang","sequence":"first","affiliation":[{"name":"Huawei Noah's Ark Lab, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8320-6845","authenticated-orcid":false,"given":"Chenxu","family":"Zhu","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab, 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\/0009-0002-2120-7273","authenticated-orcid":false,"given":"Weipeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab, 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\/0000-0002-3351-5401","authenticated-orcid":false,"given":"Xinyi","family":"Dai","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7393-8994","authenticated-orcid":false,"given":"Huifeng","family":"Guo","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab, Shenzhen, China"}]}],"member":"320","published-online":{"date-parts":[[2025,8,3]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al.","author":"Achiam Josh","year":"2023","unstructured":"Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al. 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)."},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.11.064"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/1458082.1458112"},{"key":"e_1_3_2_2_4_1","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et al. 2020. Language models are few-shot learners. Advances in neural information processing systems Vol. 33 (2020) 1877-1901."},{"key":"e_1_3_2_2_5_1","volume-title":"Large language models for text classification: From zero-shot learning to fine-tuning","author":"Chae Youngjin","year":"2023","unstructured":"Youngjin Chae and Thomas Davidson. 2023. Large language models for text classification: From zero-shot learning to fine-tuning. Open Science Foundation (2023)."},{"key":"e_1_3_2_2_6_1","volume-title":"Automatic tagging using deep convolutional neural networks. arXiv preprint arXiv:1606.00298","author":"Choi Keunwoo","year":"2016","unstructured":"Keunwoo Choi, George Fazekas, and Mark Sandler. 2016. Automatic tagging using deep convolutional neural networks. arXiv preprint arXiv:1606.00298 (2016)."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/HSI.2010.5514515"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/1864708.1864774"},{"key":"e_1_3_2_2_9_1","volume-title":"Proceedings of the 3rd international conference on natural language and speech processing. 59-66","author":"Elnagar Ashraf","year":"2019","unstructured":"Ashraf Elnagar, Omar Einea, and Ridhwan Al-Debsi. 2019. Automatic text tagging of Arabic news articles using ensemble deep learning models. In Proceedings of the 3rd international conference on natural language and speech processing. 59-66."},{"key":"e_1_3_2_2_10_1","unstructured":"Daya Guo Dejian Yang Haowei Zhang Junxiao Song Ruoyu Zhang Runxin Xu Qihao Zhu Shirong Ma Peiyi Wang Xiao Bi et al. 2025. Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning. arXiv preprint arXiv:2501.12948 (2025)."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/1882471.1882480"},{"key":"e_1_3_2_2_12_1","first-page":"897","volume-title":"Proceedings of Sixth International Congress on Information and Communication Technology: ICICT","volume":"1","author":"Hasegawa Tokutaka","year":"2021","unstructured":"Tokutaka Hasegawa and Shun Shiramatsu. 2021. BERT-Based Tagging Method for Social Issues in Web Articles. In Proceedings of Sixth International Congress on Information and Communication Technology: ICICT 2021, London, Volume 1. Springer, 897-909."},{"key":"e_1_3_2_2_13_1","volume-title":"Look before you leap: An exploratory study of uncertainty measurement for large language models. arXiv preprint arXiv:2307.10236","author":"Huang Yuheng","year":"2023","unstructured":"Yuheng Huang, Jiayang Song, Zhijie Wang, Shengming Zhao, Huaming Chen, Felix Juefei-Xu, and Lei Ma. 2023. Look before you leap: An exploratory study of uncertainty measurement for large language models. arXiv preprint arXiv:2307.10236 (2023)."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3571730"},{"key":"e_1_3_2_2_15_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. 2023a. Taggpt: Large language models are zero-shot multimodal taggers. arXiv preprint arXiv:2304.03022 (2023)."},{"key":"e_1_3_2_2_16_1","volume-title":"Conan-embedding: General Text Embedding with More and Better Negative Samples. arxiv: 2408.15710 [cs.CL] https:\/\/arxiv.org\/abs\/2408.15710","author":"Li Shiyu","year":"2024","unstructured":"Shiyu Li, Yang Tang, Shizhe Chen, and Xi Chen. 2024b. Conan-embedding: General Text Embedding with More and Better Negative Samples. arxiv: 2408.15710 [cs.CL] https:\/\/arxiv.org\/abs\/2408.15710"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/1367497.1367589"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29820"},{"key":"e_1_3_2_2_19_1","volume-title":"Towards general text embeddings with multi-stage contrastive learning. arXiv preprint arXiv:2308.03281","author":"Li Zehan","year":"2023","unstructured":"Zehan Li, Xin Zhang, Yanzhao Zhang, Dingkun Long, Pengjun Xie, and Meishan Zhang. 2023b. Towards general text embeddings with multi-stage contrastive learning. arXiv preprint arXiv:2308.03281 (2023)."},{"key":"e_1_3_2_2_20_1","unstructured":"Jianghao Lin Xinyi Dai Yunjia Xi Weiwen Liu Bo Chen Hao Zhang Yong Liu Chuhan Wu Xiangyang Li Chenxu Zhu et al. 2023. How can recommender systems benefit from large language models: A survey. ACM Transactions on Information Systems (2023)."},{"key":"e_1_3_2_2_21_1","volume-title":"Recurrent neural network for text classification with multi-task learning. arXiv preprint arXiv:1605.05101","author":"Liu Pengfei","year":"2016","unstructured":"Pengfei Liu, Xipeng Qiu, and Xuanjing Huang. 2016. Recurrent neural network for text classification with multi-task learning. arXiv preprint arXiv:1605.05101 (2016)."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/1135777.1135961"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/SIU53274.2021.9477994"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.5120\/ijca2018917395"},{"key":"e_1_3_2_2_25_1","volume-title":"Text classification via large language models. arXiv preprint arXiv:2305.08377","author":"Sun Xiaofei","year":"2023","unstructured":"Xiaofei Sun, Xiaoya Li, Jiwei Li, Fei Wu, Shangwei Guo, Tianwei Zhang, and Guoyin Wang. 2023. Text classification via large language models. arXiv preprint arXiv:2305.08377 (2023)."},{"key":"e_1_3_2_2_26_1","volume-title":"Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timoth\u00e9e Lacroix, Baptiste Rozi\u00e8re, Naman Goyal, Eric Hambro, Faisal Azhar, et al. 2023. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)."},{"key":"e_1_3_2_2_27_1","volume-title":"A unified tagging solution: Bidirectional lstm recurrent neural network with word embedding. arXiv preprint arXiv:1511.00215","author":"Wang Peilu","year":"2015","unstructured":"Peilu Wang, Yao Qian, Frank K Soong, Lei He, and Hai Zhao. 2015. A unified tagging solution: Bidirectional lstm recurrent neural network with word embedding. arXiv preprint arXiv:1511.00215 (2015)."},{"key":"e_1_3_2_2_28_1","unstructured":"Yunhe Wang Hanting Chen Yehui Tang Tianyu Guo Kai Han Ying Nie Xutao Wang Hailin Hu Zheyuan Bai Yun Wang et al. 2023a. PanGu-\u03c0: Enhancing Language Model Architectures via Nonlinearity Compensation. arXiv preprint arXiv:2312.17276 (2023)."},{"key":"e_1_3_2_2_29_1","volume-title":"Large language models are zero-shot text classifiers. arXiv preprint arXiv:2312.01044","author":"Wang Zhiqiang","year":"2023","unstructured":"Zhiqiang Wang, Yiran Pang, and Yanbin Lin. 2023b. Large language models are zero-shot text classifiers. arXiv preprint arXiv:2312.01044 (2023)."},{"key":"e_1_3_2_2_30_1","unstructured":"Shitao Xiao Zheng Liu Peitian Zhang and Niklas Muennighoff. 2023. C-Pack: Packaged Resources To Advance General Chinese Embedding. arxiv: 2309.07597 [cs.CL]"},{"key":"e_1_3_2_2_31_1","unstructured":"Wei Zeng Xiaozhe Ren Teng Su Hui Wang Yi Liao Zhiwei Wang Xin Jiang ZhenZhang Yang Kaisheng Wang Xiaoda Zhang et al. 2021. Pangu-\u03b1 : Large-scale autoregressive pretrained Chinese language models with auto-parallel computation. arXiv preprint arXiv:2104.12369 (2021)."},{"key":"e_1_3_2_2_32_1","volume-title":"A sensitivity analysis of (and practitioners' guide to) convolutional neural networks for sentence classification. arXiv preprint arXiv:1510.03820","author":"Zhang Ye","year":"2015","unstructured":"Ye Zhang and Byron Wallace. 2015. A sensitivity analysis of (and practitioners' guide to) convolutional neural networks for sentence classification. arXiv preprint arXiv:1510.03820 (2015)."},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11390-011-0176-1"},{"key":"e_1_3_2_2_34_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, Haonan Chen, Zheng Liu, Zhicheng Dou, and Ji-Rong Wen. 2023. Large language models for information retrieval: A survey. arXiv preprint arXiv:2308.07107 (2023)."},{"key":"e_1_3_2_2_35_1","volume-title":"ICXML: An in-context learning framework for zero-shot extreme multi-label classification. arXiv preprint arXiv:2311.09649","author":"Zhu Yaxin","year":"2023","unstructured":"Yaxin Zhu and Hamed Zamani. 2023. ICXML: An in-context learning framework for zero-shot extreme multi-label classification. arXiv preprint arXiv:2311.09649 (2023)."}],"event":{"name":"KDD '25: The 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Toronto ON Canada","acronym":"KDD '25","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3711896.3737242","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,16]],"date-time":"2025-08-16T14:42:19Z","timestamp":1755355339000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3711896.3737242"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,3]]},"references-count":35,"alternative-id":["10.1145\/3711896.3737242","10.1145\/3711896"],"URL":"https:\/\/doi.org\/10.1145\/3711896.3737242","relation":{},"subject":[],"published":{"date-parts":[[2025,8,3]]},"assertion":[{"value":"2025-08-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}