{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T18:38:43Z","timestamp":1771267123279,"version":"3.50.1"},"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":[[2026,2,22]]},"DOI":"10.1145\/3773966.3778009","type":"proceedings-article","created":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T17:50:01Z","timestamp":1771264201000},"page":"69-78","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Large Language Model Judged Self-Training for Named Entity Recognition"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-0368-6866","authenticated-orcid":false,"given":"Shisong","family":"Chen","sequence":"first","affiliation":[{"name":"Shanghai Institute of Artificial Intelligence for Education, East China Normal University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2587-7648","authenticated-orcid":false,"given":"Jiaan","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7023-7543","authenticated-orcid":false,"given":"Chengyi","family":"Yang","sequence":"additional","affiliation":[{"name":"Shanghai Institute of Artificial Intelligence for Education, East China Normal University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8403-9591","authenticated-orcid":false,"given":"Yanghua","family":"Xiao","sequence":"additional","affiliation":[{"name":"Shanghai Key Laboratory of Data Science, School of Computer Science, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2355-288X","authenticated-orcid":false,"given":"Zhixu","family":"Li","sequence":"additional","affiliation":[{"name":"School of Information, Renmin University of China, Beijing, China and School of Smart Governance, Renmin University of China, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4110-8989","authenticated-orcid":false,"given":"Xin","family":"Lin","sequence":"additional","affiliation":[{"name":"Shanghai Institute of Artificial Intelligence for Education, East China Normal University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,2,21]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Self-training: A survey. ArXiv preprint","author":"Amini Massih-Reza","year":"2022","unstructured":"Massih-Reza Amini, Vasilii Feofanov, Loic Pauletto, Emilie Devijver, and Yury Maximov. 2022. Self-training: A survey. ArXiv preprint, Vol. abs\/2202.12040 (2022). https:\/\/arxiv.org\/abs\/2202.12040"},{"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 Binyuan Hui Luo Ji Mei Li Junyang Lin Runji Lin Dayiheng Liu Gao Liu Chengqiang Lu Keming Lu Jianxin Ma Rui Men Xingzhang Ren Xuancheng Ren Chuanqi Tan Sinan Tan Jianhong Tu Peng Wang Shijie Wang Wei Wang Shengguang Wu Benfeng Xu Jin Xu An Yang Hao Yang Jian Yang Shusheng Yang Yang Yao Bowen Yu Hongyi Yuan Zheng Yuan Jianwei Zhang Xingxuan Zhang Yichang Zhang Zhenru Zhang Chang Zhou Jingren Zhou Xiaohuan Zhou and Tianhang Zhu. 2023. Qwen Technical Report. arXiv preprint arXiv:2309.16609 (2023)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1002\/9780470316870"},{"key":"e_1_3_2_1_4_1","volume-title":"Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020","author":"Brown Tom B.","year":"2020","unstructured":"Tom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel M. Ziegler, Jeffrey Wu, Clemens Winter, Christopher Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, and Dario Amodei. 2020. Language Models are Few-Shot Learners. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual, Hugo Larochelle, Marc'Aurelio Ranzato, Raia Hadsell, Maria-Florina Balcan, and Hsuan-Tien Lin (Eds.). https:\/\/proceedings.neurips.cc\/paper\/2020\/hash\/1457c0d6bfcb4967418bfb8ac142f64a-Abstract.html"},{"key":"e_1_3_2_1_5_1","first-page":"32424","article-title":"Debiased self-training for semi-supervised learning","volume":"35","author":"Chen Baixu","year":"2022","unstructured":"Baixu Chen, Junguang Jiang, Ximei Wang, Pengfei Wan, Jianmin Wang, and Mingsheng Long. 2022. Debiased self-training for semi-supervised learning. Advances in Neural Information Processing Systems, Vol. 35 (2022), 32424-32437.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_6_1","volume-title":"MLLM-as-a-Judge: Assessing Multimodal LLM-as-a-Judge with Vision-Language Benchmark. arXiv preprint arXiv:2402.04788","author":"Chen Dongping","year":"2024","unstructured":"Dongping Chen, Ruoxi Chen, Shilin Zhang, Yinuo Liu, Yaochen Wang, Huichi Zhou, Qihui Zhang, Pan Zhou, Yao Wan, and Lichao Sun. 2024. MLLM-as-a-Judge: Assessing Multimodal LLM-as-a-Judge with Vision-Language Benchmark. arXiv preprint arXiv:2402.04788 (2024)."},{"key":"e_1_3_2_1_7_1","volume-title":"Can Large Language Models Be an Alternative to Human Evaluations? arXiv preprint arXiv:2305.01937","author":"Chiang Cheng-Han","year":"2023","unstructured":"Cheng-Han Chiang and Hung-yi Lee. 2023. Can Large Language Models Be an Alternative to Human Evaluations? arXiv preprint arXiv:2305.01937 (2023)."},{"key":"e_1_3_2_1_8_1","unstructured":"Alice Coucke Alaa Saade Adrien Ball Th\u00e9odore Bluche Alexandre Caulier David Leroy Cl\u00e9ment Doumouro Thibault Gisselbrecht Francesco Caltagirone Thibaut Lavril et al. 2018. Snips voice platform: an embedded spoken language understanding system for private-by-design voice interfaces. arXiv preprint arXiv:1805.10190 (2018)."},{"key":"e_1_3_2_1_9_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00087"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3250828"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0246310"},{"key":"e_1_3_2_1_13_1","volume-title":"Xiezhi: An Ever-Updating Benchmark for Holistic Domain Knowledge Evaluation. ArXiv preprint","author":"Gu Zhouhong","year":"2023","unstructured":"Zhouhong Gu, Xiaoxuan Zhu, Haoning Ye, Lin Zhang, Jianchen Wang, Sihang Jiang, Zhuozhi Xiong, Zihan Li, Qianyu He, Rui Xu, et al., 2023. Xiezhi: An Ever-Updating Benchmark for Holistic Domain Knowledge Evaluation. ArXiv preprint, Vol. abs\/2306.05783 (2023). https:\/\/arxiv.org\/abs\/2306.05783"},{"key":"e_1_3_2_1_14_1","volume-title":"Proggen: Generating named entity recognition datasets step-by-step with self-reflexive large language models. arXiv preprint arXiv:2403.11103","author":"Heng Yuzhao","year":"2024","unstructured":"Yuzhao Heng, Chunyuan Deng, Yitong Li, Yue Yu, Yinghao Li, Rongzhi Zhang, and Chao Zhang. 2024. Proggen: Generating named entity recognition datasets step-by-step with self-reflexive large language models. arXiv preprint arXiv:2403.11103 (2024)."},{"key":"e_1_3_2_1_15_1","volume-title":"Prompt-Based Self-training Framework for Few-Shot Named Entity Recognition. In International Conference on Knowledge Science, Engineering and Management. Springer, 91-103","author":"Huang Ganghong","year":"2022","unstructured":"Ganghong Huang, Jiang Zhong, Chen Wang, Qizhu Dai, and Rongzhen Li. 2022. Prompt-Based Self-training Framework for Few-Shot Named Entity Recognition. In International Conference on Knowledge Science, Engineering and Management. Springer, 91-103."},{"key":"e_1_3_2_1_16_1","unstructured":"Lei Huang Weijiang Yu Weitao Ma Weihong Zhong Zhangyin Feng Haotian Wang Qianglong Chen Weihua Peng Xiaocheng Feng Bing Qin et al. 2023. A survey on hallucination in large language models: Principles taxonomy challenges and open questions. arXiv preprint arXiv:2311.05232 (2023)."},{"key":"e_1_3_2_1_17_1","volume-title":"Diego de las Casas, Emma Bou Hanna, Florian Bressand, et al.","author":"Jiang Albert Q","year":"2024","unstructured":"Albert Q Jiang, Alexandre Sablayrolles, Antoine Roux, Arthur Mensch, Blanche Savary, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Emma Bou Hanna, Florian Bressand, et al., 2024. Mixtral of experts. arXiv preprint arXiv:2401.04088 (2024)."},{"key":"e_1_3_2_1_18_1","unstructured":"Saurav Kadavath Tom Conerly Amanda Askell Tom Henighan Dawn Drain Ethan Perez Nicholas Schiefer Zac Hatfield-Dodds Nova DasSarma Eli Tran-Johnson et al. 2022. Language models (mostly) know what they know. arXiv preprint arXiv:2207.05221 (2022)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1631\/FITEE.1800743"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403149"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639301"},{"key":"e_1_3_2_1_22_1","volume-title":"Critique ability of large language models. arXiv preprint arXiv:2310.04815","author":"Luo Liangchen","year":"2023","unstructured":"Liangchen Luo, Zi Lin, Yinxiao Liu, Lei Shu, Yun Zhu, Jingbo Shang, and Lei Meng. 2023. Critique ability of large language models. arXiv preprint arXiv:2310.04815 (2023)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"crossref","unstructured":"Sewon Min Xinxi Lyu Ari Holtzman Mikel Artetxe Mike Lewis Hannaneh Hajishirzi and Luke Zettlemoyer. 2022. Rethinking the Role of Demonstrations: What makes In-context Learning Work?. In EMNLP.","DOI":"10.18653\/v1\/2022.emnlp-main.759"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1075\/li.30.1.03nad"},{"key":"e_1_3_2_1_25_1","volume-title":"Leveraging Ensemble Diversity for Robust Self-Training in the Presence of Sample Selection Bias. ArXiv preprint","author":"Odonnat Ambroise","year":"2023","unstructured":"Ambroise Odonnat, Vasilii Feofanov, and Ievgen Redko. 2023. Leveraging Ensemble Diversity for Robust Self-Training in the Presence of Sample Selection Bias. ArXiv preprint, Vol. abs\/2310.14814 (2023). https:\/\/arxiv.org\/abs\/2310.14814"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.191"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.3115\/1119176.1119195"},{"key":"e_1_3_2_1_28_1","volume-title":"Llamas Know What GPTs Don't Show: Surrogate Models for Confidence Estimation. arXiv preprint arXiv:2311.08877","author":"Shrivastava Vaishnavi","year":"2023","unstructured":"Vaishnavi Shrivastava, Percy Liang, and Ananya Kumar. 2023. Llamas Know What GPTs Don't Show: Surrogate Models for Confidence Estimation. arXiv preprint arXiv:2311.08877 (2023)."},{"key":"e_1_3_2_1_29_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_1_30_1","unstructured":"Anbang Wang Difei Mei Zhichao Zhang Xiuxiu Bai Ran Yao Zewen Fang Min Hu Zhirui Cao Haitao Sun Yifeng Guo et al. 2024. ReverseNER: A Self-Generated Example-Driven Framework for Zero-Shot Named Entity Recognition with Large Language Models. arXiv preprint arXiv:2411.00533 (2024)."},{"key":"e_1_3_2_1_31_1","volume-title":"Uncertainty-aware Self-training for Low-resource Neural Sequence Labeling. arXiv preprint arXiv:2302.08659","author":"Wang Jianing","year":"2023","unstructured":"Jianing Wang, Chengyu Wang, Jun Huang, Ming Gao, and Aoying Zhou. 2023b. Uncertainty-aware Self-training for Low-resource Neural Sequence Labeling. arXiv preprint arXiv:2302.08659 (2023)."},{"key":"e_1_3_2_1_32_1","volume-title":"Gpt-ner: Named entity recognition via large language models. ArXiv preprint","author":"Wang Shuhe","year":"2023","unstructured":"Shuhe Wang, Xiaofei Sun, Xiaoya Li, Rongbin Ouyang, Fei Wu, Tianwei Zhang, Jiwei Li, and Guoyin Wang. 2023a. Gpt-ner: Named entity recognition via large language models. ArXiv preprint, Vol. abs\/2304.10428 (2023). https:\/\/arxiv.org\/abs\/2304.10428"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467235"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.167"},{"key":"e_1_3_2_1_35_1","volume-title":"Self-improving for zero-shot named entity recognition with large language models. arXiv preprint arXiv:2311.08921","author":"Xie Tingyu","year":"2023","unstructured":"Tingyu Xie, Qi Li, Yan Zhang, Zuozhu Liu, and Hongwei Wang. 2023. Self-improving for zero-shot named entity recognition with large language models. arXiv preprint arXiv:2311.08921 (2023)."},{"key":"e_1_3_2_1_36_1","volume-title":"Small models are valuable plug-ins for large language models. ArXiv preprint","author":"Xu Canwen","year":"2023","unstructured":"Canwen Xu, Yichong Xu, Shuohang Wang, Yang Liu, Chenguang Zhu, and Julian McAuley. 2023. Small models are valuable plug-ins for large language models. ArXiv preprint, Vol. abs\/2305.08848 (2023). https:\/\/arxiv.org\/abs\/2305.08848"},{"key":"e_1_3_2_1_37_1","volume-title":"International Conference on Pattern Recognition. Springer, 399-411","author":"Yan Faren","year":"2024","unstructured":"Faren Yan, Peng Yu, and Xin Chen. 2024. LTNER: Large language model tagging for named entity recognition with contextualized entity marking. In International Conference on Pattern Recognition. Springer, 399-411."},{"key":"e_1_3_2_1_38_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 Vol. abs\/2303.18223 (2023). https:\/\/arxiv.org\/abs\/2303.18223"},{"key":"e_1_3_2_1_39_1","unstructured":"Lianmin Zheng Wei-Lin Chiang Ying Sheng Siyuan Zhuang Zhanghao Wu Yonghao Zhuang Zi Lin Zhuohan Li Dacheng Li Eric Xing et al. 2023. Judging LLM-as-a-judge with MT-Bench and Chatbot Arena. arXiv preprint arXiv:2306.05685 (2023)."}],"event":{"name":"WSDM '26:The Nineteenth ACM International Conference on Web Search and Data Mining","location":"Boise ID USA","sponsor":["SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGIR ACM Special Interest Group on Information Retrieval","SIGMOD ACM Special Interest Group on Management of Data"]},"container-title":["Proceedings of the Nineteenth ACM International Conference on Web Search and Data Mining"],"original-title":[],"deposited":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T17:51:42Z","timestamp":1771264302000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3773966.3778009"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,21]]},"references-count":39,"alternative-id":["10.1145\/3773966.3778009","10.1145\/3773966"],"URL":"https:\/\/doi.org\/10.1145\/3773966.3778009","relation":{},"subject":[],"published":{"date-parts":[[2026,2,21]]},"assertion":[{"value":"2026-02-21","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}