{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T17:27:16Z","timestamp":1784050036165,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":66,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,8,3]]},"DOI":"10.1145\/3711896.3736829","type":"proceedings-article","created":{"date-parts":[[2025,8,3]],"date-time":"2025-08-03T20:54:17Z","timestamp":1754254457000},"page":"1541-1552","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Adapting Pretrained Language Models for Citation Classification via Self-Supervised Contrastive Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-6486-8528","authenticated-orcid":false,"given":"Tong","family":"Li","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Kowloon, Hong Kong SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6473-8221","authenticated-orcid":false,"given":"Jiachuan","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Kowloon, Hong Kong SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2085-7418","authenticated-orcid":false,"given":"Yongqi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Thrust of Data Science And Analytics, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6404-3438","authenticated-orcid":false,"given":"Shuangyin","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science, South China Normal University, Guangzhou, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8257-5806","authenticated-orcid":false,"given":"Lei","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Kowloon, Hong Kong SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,8,3]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11192-018-2920-6"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2689925"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1371"},{"key":"e_1_3_2_2_4_1","volume-title":"Longformer: The long-document transformer. arXiv preprint arXiv:2004.05150","author":"Beltagy Iz","year":"2020","unstructured":"Iz Beltagy, Matthew E Peters, and Arman Cohan. 2020. Longformer: The long-document transformer. arXiv preprint arXiv:2004.05150 (2020)."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3487553.3524657"},{"key":"e_1_3_2_2_6_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_7_1","volume-title":"arXiv preprint arXiv:2406.08660","author":"Jos\u00e9 Bucher Martin Juan","year":"2024","unstructured":"Martin Juan Jos\u00e9 Bucher and Marco Martini. 2024. Fine-Tuned'Small'LLMs (Still) Significantly Outperform Zero-Shot Generative AI Models in Text Classification. arXiv preprint arXiv:2406.08660 (2024)."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.4261"},{"key":"e_1_3_2_2_9_1","unstructured":"Liang Chen Zekun Wang Shuhuai Ren Lei Li Haozhe Zhao Yunshui Li Zefan Cai Hongcheng Guo Lei Zhang Yizhe Xiong et al. 2024. Next Token Prediction Towards Multimodal Intelligence: A Comprehensive Survey. arXiv preprint arXiv:2412.18619 (2024)."},{"key":"e_1_3_2_2_10_1","volume-title":"International conference on machine learning. PMLR, 1597-1607","author":"Chen Ting","year":"2020","unstructured":"Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey Hinton. 2020. A simple framework for contrastive learning of visual representations. In International conference on machine learning. PMLR, 1597-1607."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1361"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.207"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00799-017-0216-8"},{"key":"e_1_3_2_2_14_1","unstructured":"Alexis Conneau Douwe Kiela Holger Schwenk Loic Barrault and Antoine Bordes. 2018. Supervised Learning of Universal Sentence Representations from Natural Language Inference Data. arxiv: 1705.02364 [cs.CL] https:\/\/arxiv.org\/abs\/1705.02364"},{"key":"e_1_3_2_2_15_1","volume-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. CoRR","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. CoRR, Vol. abs\/1810.04805 (2018). showeprint[arXiv]1810.04805 http:\/\/arxiv.org\/abs\/1810.04805"},{"key":"e_1_3_2_2_16_1","volume-title":"Improved Regularization of Convolutional Neural Networks with Cutout. arXiv preprint arXiv:1708.04552","author":"DeVries Terrance","year":"2017","unstructured":"Terrance DeVries. 2017. Improved Regularization of Convolutional Neural Networks with Cutout. arXiv preprint arXiv:1708.04552 (2017)."},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE53745.2022.00322"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.wiesp-1.17"},{"key":"e_1_3_2_2_19_1","unstructured":"Zeyu Han Chao Gao Jinyang Liu Jeff Zhang and Sai Qian Zhang. 2024. Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey. arxiv: 2403.14608 [cs.LG] https:\/\/arxiv.org\/abs\/2403.14608"},{"key":"e_1_3_2_2_20_1","volume-title":"HLM-Cite: Hybrid Language Model Workflow for Text-based Scientific Citation Prediction. In The Thirty-eighth Annual Conference on Neural Information Processing Systems.","author":"Hao Qianyue","year":"2024","unstructured":"Qianyue Hao, Jingyang Fan, Fengli Xu, Jian Yuan, and Yong Li. 2024. HLM-Cite: Hybrid Language Model Workflow for Text-based Scientific Citation Prediction. In The Thirty-eighth Annual Conference on Neural Information Processing Systems."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11192-018-2767-x"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/1772690.1772734"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1017\/S1351324915000388"},{"key":"e_1_3_2_2_24_1","volume-title":"Parameter-Efficient Transfer Learning for NLP. arxiv","author":"Houlsby Neil","year":"1902","unstructured":"Neil Houlsby, Andrei Giurgiu, Stanislaw Jastrzebski, Bruna Morrone, Quentin de Laroussilhe, Andrea Gesmundo, Mona Attariyan, and Sylvain Gelly. 2019. Parameter-Efficient Transfer Learning for NLP. arxiv: 1902.00751 [cs.LG] https:\/\/arxiv.org\/abs\/1902.00751"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1017\/S1351324915000443"},{"key":"e_1_3_2_2_26_1","volume-title":"Scaling sentence embeddings with large language models. arXiv preprint arXiv:2307.16645","author":"Jiang Ting","year":"2023","unstructured":"Ting Jiang, Shaohan Huang, Zhongzhi Luan, Deqing Wang, and Fuzhen Zhuang. 2023. Scaling sentence embeddings with large language models. arXiv preprint arXiv:2307.16645 (2023)."},{"key":"e_1_3_2_2_27_1","first-page":"7005","volume-title":"PATTON: Language Model Pretraining on Text-Rich Networks. In 61st Annual Meeting of the Association for Computational Linguistics, ACL","author":"Jin Bowen","year":"2023","unstructured":"Bowen Jin, Wentao Zhang, Yu Zhang, Yu Meng, Xinyang Zhang, Qi Zhu, and Jiawei Han. 2023. PATTON: Language Model Pretraining on Text-Rich Networks. In 61st Annual Meeting of the Association for Computational Linguistics, ACL 2023. Association for Computational Linguistics (ACL), 7005-7020."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00028"},{"key":"e_1_3_2_2_29_1","volume-title":"Logistic regression in rare events data. Political analysis","author":"King Gary","year":"2001","unstructured":"Gary King and Langche Zeng. 2001. Logistic regression in rare events data. Political analysis, Vol. 9, 2 (2001), 137-163."},{"key":"e_1_3_2_2_30_1","volume-title":"A meta-analysis of semantic classification of citations. Quantitative science studies","author":"Kunnath Suchetha N","year":"2021","unstructured":"Suchetha N Kunnath, Drahomira Herrmannova, David Pride, and Petr Knoth. 2021a. A meta-analysis of semantic classification of citations. Quantitative science studies, Vol. 2, 4 (2021), 1170-1215."},{"key":"e_1_3_2_2_31_1","volume-title":"Overview of the 2021 SDP 3C citation context classification shared task","author":"Kunnath Suchetha N","unstructured":"Suchetha N Kunnath, David Pride, Drahomira Herrmannova, and Petr Knoth. 2021b. Overview of the 2021 SDP 3C citation context classification shared task. Association for Computational Linguistics."},{"key":"e_1_3_2_2_32_1","volume-title":"Proceedings of the 2nd Conference of the Asia-Pacific","author":"Kunnath Suchetha Nambanoor","unstructured":"Suchetha Nambanoor Kunnath, David Pride, and Petr Knoth. 2022a. Dynamic Context Extraction for Citation Classification. In Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 539-549."},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3615018"},{"key":"e_1_3_2_2_34_1","volume-title":"Proceedings of the Thirteenth Language Resources and Evaluation Conference. 3398-3406","author":"Kunnath Suchetha Nambanoor","year":"2022","unstructured":"Suchetha Nambanoor Kunnath, Valentin Stauber, Ronin Wu, David Pride, Viktor Botev, and Petr Knoth. 2022b. ACT2: A multi-disciplinary semi-structured dataset for importance and purpose classification of citations. In Proceedings of the Thirteenth Language Resources and Evaluation Conference. 3398-3406."},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-naacl.253"},{"key":"e_1_3_2_2_36_1","volume-title":"Meta-task prompting elicits embedding from large language models. arXiv preprint arXiv:2402.18458","author":"Lei Yibin","year":"2024","unstructured":"Yibin Lei, Di Wu, Tianyi Zhou, Tao Shen, Yu Cao, Chongyang Tao, and Andrew Yates. 2024. Meta-task prompting elicits embedding from large language models. arXiv preprint arXiv:2402.18458 (2024)."},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00638"},{"key":"e_1_3_2_2_38_1","first-page":"2824","article-title":"Cutting Down on Prompts and Parameters: Simple Few-Shot Learning with Language Models","volume":"2022","author":"Ivana Bala\u017eevi\u0107 Robert Logan IV","year":"2022","unstructured":"Robert Logan IV, Ivana Bala\u017eevi\u0107, Eric Wallace, Fabio Petroni, Sameer Singh, and Sebastian Riedel. 2022. Cutting Down on Prompts and Parameters: Simple Few-Shot Learning with Language Models. In Findings of the Association for Computational Linguistics: ACL 2022. 2824-2835.","journal-title":"Findings of the Association for Computational Linguistics: ACL"},{"key":"e_1_3_2_2_39_1","volume-title":"Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101","author":"Loshchilov Ilya","year":"2017","unstructured":"Ilya Loshchilov and Frank Hutter. 2017. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)."},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.166"},{"key":"e_1_3_2_2_41_1","volume-title":"Proceedings of the Second Workshop on Scholarly Document Processing. 130-133","author":"Maheshwari Himanshu","year":"2021","unstructured":"Himanshu Maheshwari, Bhavyajeet Singh, and Vasudeva Varma. 2021. SciBERT sentence representation for citation context classification. In Proceedings of the Second Workshop on Scholarly Document Processing. 130-133."},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/219717.219748"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1162\/qss_a_00146"},{"key":"e_1_3_2_2_44_1","volume-title":"Citation analysis. Annual review of information science and technology","author":"Nicolaisen Jeppe","year":"2007","unstructured":"Jeppe Nicolaisen. 2007. Citation analysis. Annual review of information science and technology, Vol. 41, 1 (2007), 609-641."},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11192-024-05142-9"},{"key":"e_1_3_2_2_46_1","volume-title":"Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748","author":"van den Oord Aaron","year":"2018","unstructured":"Aaron van den Oord, Yazhe Li, and Oriol Vinyals. 2018. Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)."},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"e_1_3_2_2_48_1","first-page":"125","volume-title":"8th international workshop on bibliometric-enhanced information retrieval (bir) co-located with the 41st european conference on information retrieval (ecir","volume":"2345","author":"Perier-Camby Julien","year":"2019","unstructured":"Julien Perier-Camby, Marc Bertin, Iana Atanassova, and Fr\u00e9d\u00e9ric Armetta. 2019. A preliminary study to compare deep learning with rule-based approaches for citation classification. In 8th international workshop on bibliometric-enhanced information retrieval (bir) co-located with the 41st european conference on information retrieval (ecir 2019), Vol. 2345. 125-131."},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/345508.345563"},{"key":"e_1_3_2_2_50_1","volume-title":"Deep contextualized word representations. arxiv","author":"Peters Matthew E.","year":"1802","unstructured":"Matthew E. Peters, Mark Neumann, Mohit Iyyer, Matt Gardner, Christopher Clark, Kenton Lee, and Luke Zettlemoyer. 2018. Deep contextualized word representations. arxiv: 1802.05365 [cs.CL] https:\/\/arxiv.org\/abs\/1802.05365"},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3383583.3398617"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/JCDL.2019.00055"},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/2623330.2623630"},{"key":"e_1_3_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3050547"},{"key":"e_1_3_2_2_55_1","volume-title":"Fine-Tuning Language Models on Multiple Datasets for Citation Intention Classification. arXiv preprint arXiv:2410.13332","author":"Shui Zeren","year":"2024","unstructured":"Zeren Shui, Petros Karypis, Daniel S Karls, Mingjian Wen, Saurav Manchanda, Ellad B Tadmor, and George Karypis. 2024. Fine-Tuning Language Models on Multiple Datasets for Citation Intention Classification. arXiv preprint arXiv:2410.13332 (2024)."},{"key":"e_1_3_2_2_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/3041021.3051105"},{"key":"e_1_3_2_2_57_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.573"},{"key":"e_1_3_2_2_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3614808"},{"key":"e_1_3_2_2_59_1","volume-title":"Workshops at the twenty-ninth AAAI conference on artificial intelligence.","author":"Valenzuela Marco","year":"2015","unstructured":"Marco Valenzuela, Vu Ha, and Oren Etzioni. 2015. Identifying meaningful citations. In Workshops at the twenty-ninth AAAI conference on artificial intelligence."},{"key":"e_1_3_2_2_60_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1670"},{"key":"e_1_3_2_2_61_1","volume-title":"Clear: Contrastive learning for sentence representation. arXiv preprint arXiv:2012.15466","author":"Wu Zhuofeng","year":"2020","unstructured":"Zhuofeng Wu, Sinong Wang, Jiatao Gu, Madian Khabsa, Fei Sun, and Hao Ma. 2020. Clear: Contrastive learning for sentence representation. arXiv preprint arXiv:2012.15466 (2020)."},{"key":"e_1_3_2_2_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380175"},{"key":"e_1_3_2_2_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389632"},{"key":"e_1_3_2_2_64_1","volume-title":"PST-Bench: Tracing and Benchmarking the Source of Publications. arXiv preprint arXiv:2402.16009","author":"Zhang Fanjin","year":"2024","unstructured":"Fanjin Zhang, Kun Cao, Yukuo Cen, Jifan Yu, Da Yin, and Jie Tang. 2024. PST-Bench: Tracing and Benchmarking the Source of Publications. arXiv preprint arXiv:2402.16009 (2024)."},{"key":"e_1_3_2_2_65_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.820"},{"key":"e_1_3_2_2_66_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331348"}],"event":{"name":"KDD '25: The 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Toronto ON Canada","acronym":"KDD '25","sponsor":["SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGMOD ACM Special Interest Group on Management of 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\/3711896.3736829","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T18:12:24Z","timestamp":1777572744000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3711896.3736829"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,3]]},"references-count":66,"alternative-id":["10.1145\/3711896.3736829","10.1145\/3711896"],"URL":"https:\/\/doi.org\/10.1145\/3711896.3736829","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"}}]}}