{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T04:10:44Z","timestamp":1763007044490,"version":"3.45.0"},"publisher-location":"Singapore","reference-count":33,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819530540","type":"print"},{"value":"9789819530557","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T00:00:00Z","timestamp":1763078400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T00:00:00Z","timestamp":1763078400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-981-95-3055-7_24","type":"book-chapter","created":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T04:07:32Z","timestamp":1763006852000},"page":"307-318","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Evaluating LLMs for\u00a0Multi-label Text Classification"],"prefix":"10.1007","author":[{"given":"Mengqi","family":"Wang","sequence":"first","affiliation":[]},{"given":"Ming","family":"Liu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,11,14]]},"reference":[{"key":"24_CR1","doi-asserted-by":"publisher","unstructured":"Ashktorab, Z., et al.: Fairness evaluation in text classification: machine learning practitioner perspectives of individual and group fairness. In: Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems, CHI 2023. Association for Computing Machinery, New York (2023). https:\/\/doi.org\/10.1145\/3544548.3581227","DOI":"10.1145\/3544548.3581227"},{"key":"24_CR2","doi-asserted-by":"crossref","unstructured":"Be\u021bianu, M., M\u0103lan, A., Aldinucci, M., Birke, R., Chen, L.: DALLMi: domain adaption for LLM-based multi-label classifier. In: Pacific-Asia Conference on Knowledge Discovery and Data Mining, pp. 277\u2013289. Springer (2024)","DOI":"10.1007\/978-981-97-2259-4_21"},{"key":"24_CR3","doi-asserted-by":"crossref","unstructured":"Caselli, T., Basile, V., Mitrovi\u0107, J., Granitzer, M.: HateBERT: retraining BERT for abusive language detection in English. arXiv preprint arXiv:2010.12472 (2020)","DOI":"10.18653\/v1\/2021.woah-1.3"},{"key":"24_CR4","unstructured":"Chen, S., et al.: Evaluation of chatGPT family of models for biomedical reasoning and classification. arXiv preprint arXiv:2304.02496 (2023)"},{"key":"24_CR5","unstructured":"Chiu, K.L., Collins, A., Alexander, R.: Detecting hate speech with GPT-3. arXiv preprint arXiv:2103.12407 (2021)"},{"key":"24_CR6","unstructured":"Dai, H., et\u00a0al.: ChatAug: leveraging chatGPT for text data augmentation. arXiv preprint arXiv:2302.13007 (2023). 1(2)"},{"key":"24_CR7","doi-asserted-by":"crossref","unstructured":"Davidson, T., Warmsley, D., Macy, M., Weber, I.: Automated hate speech detection and the problem of offensive language. In: Proceedings of the international AAAI Conference on Web and Social Media, vol.\u00a011, pp. 512\u2013515 (2017)","DOI":"10.1609\/icwsm.v11i1.14955"},{"key":"24_CR8","unstructured":"Devlin, J.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"24_CR9","doi-asserted-by":"crossref","unstructured":"Druck, G., Settles, B., McCallum, A.: Active learning by labeling features. In: Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing, pp. 81\u201390 (2009)","DOI":"10.3115\/1699510.1699522"},{"key":"24_CR10","doi-asserted-by":"publisher","unstructured":"Dwork, C., Hardt, M., Pitassi, T., Reingold, O., Zemel, R.: Fairness through awareness. In: Proceedings of the 3rd Innovations in Theoretical Computer Science Conference, pp. 214\u2013226, ITCS 2012. Association for Computing Machinery, New York (2012). https:\/\/doi.org\/10.1145\/2090236.2090255","DOI":"10.1145\/2090236.2090255"},{"key":"24_CR11","doi-asserted-by":"publisher","unstructured":"ElSherief, M., et al.: Latent hatred: a benchmark for understanding implicit hate speech. In: Moens, M.F., Huang, X., Specia, L., Yih, S.W.t. (eds.) Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, Online and Punta Cana, Dominican Republic, pp. 345\u2013363. Association for Computational Linguistics (2021). https:\/\/doi.org\/10.18653\/v1\/2021.emnlp-main.29. https:\/\/aclanthology.org\/2021.emnlp-main.29","DOI":"10.18653\/v1\/2021.emnlp-main.29"},{"issue":"30","key":"24_CR12","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2305016120","volume":"120","author":"F Gilardi","year":"2023","unstructured":"Gilardi, F., Alizadeh, M., Kubli, M.: ChatGPT outperforms crowd workers for text-annotation tasks. Proc. Natl. Acad. Sci. 120(30), e2305016120 (2023)","journal-title":"Proc. Natl. Acad. Sci."},{"key":"24_CR13","doi-asserted-by":"crossref","unstructured":"Huang, J., Huang, K.: ChatGPT in government. In: Beyond AI: ChatGPT, Web3, and the Business Landscape of Tomorrow, pp. 271\u2013294. Springer (2023)","DOI":"10.1007\/978-3-031-45282-6_10"},{"issue":"W1","key":"24_CR14","doi-asserted-by":"publisher","first-page":"W5","DOI":"10.1093\/nar\/gkaa333","volume":"48","author":"R Islamaj","year":"2020","unstructured":"Islamaj, R., Kwon, D., Kim, S., Lu, Z.: TeamTat: a collaborative text annotation tool. Nucleic Acids Res. 48(W1), W5\u2013W11 (2020)","journal-title":"Nucleic Acids Res."},{"key":"24_CR15","doi-asserted-by":"crossref","unstructured":"Kholodna, N., Julka, S., Khodadadi, M., Gumus, M.N., Granitzer, M.: LLMs in the loop: leveraging large language model annotations for active learning in low-resource languages. In: Joint European Conference on Machine Learning and Knowledge Discovery in Databases, pp. 397\u2013412. Springer (2024)","DOI":"10.1007\/978-3-031-70381-2_25"},{"key":"24_CR16","doi-asserted-by":"crossref","unstructured":"Kirk, H.R., Birhane, A., Vidgen, B., Derczynski, L.: Handling and presenting harmful text in NLP research. arXiv preprint arXiv:2204.14256 (2022)","DOI":"10.18653\/v1\/2022.findings-emnlp.35"},{"key":"24_CR17","unstructured":"Kuzman, T., Mozetic, I., Ljube\u0161ic, N.: ChatGPT: beginning of an end of manual linguistic data annotation. Use Case of Automatic Genre Identification. ArXiv abs\/2303.03953 (2023)"},{"key":"24_CR18","doi-asserted-by":"publisher","unstructured":"Lertvittayakumjorn, P., Specia, L., Toni, F.: FIND: human-in-the-loop debugging deep text classifiers. In: Webber, B., Cohn, T., He, Y., Liu, Y. (eds.) Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 332\u2013348. Association for Computational Linguistics, Online (2020). https:\/\/doi.org\/10.18653\/v1\/2020.emnlp-main.24. https:\/\/aclanthology.org\/2020.emnlp-main.24","DOI":"10.18653\/v1\/2020.emnlp-main.24"},{"key":"24_CR19","doi-asserted-by":"publisher","first-page":"128339","DOI":"10.1109\/ACCESS.2019.2939488","volume":"7","author":"J Liu","year":"2019","unstructured":"Liu, J., et al.: Multi-component fusion network for small object detection in remote sensing images. IEEE Access 7, 128339\u2013128352 (2019)","journal-title":"IEEE Access"},{"key":"24_CR20","unstructured":"Luo, Z., Xie, Q., Ananiadou, S.: ChatGPT as a factual inconsistency evaluator for text summarization. arXiv preprint arXiv:2303.15621 (2023)"},{"issue":"9","key":"24_CR21","doi-asserted-by":"publisher","first-page":"3046","DOI":"10.3390\/s21093046","volume":"21","author":"S Minaee","year":"2021","unstructured":"Minaee, S., Minaei, M., Abdolrashidi, A.: Deep-emotion: facial expression recognition using attentional convolutional network. Sensors 21(9), 3046 (2021)","journal-title":"Sensors"},{"key":"24_CR22","unstructured":"Mollas, I., Chrysopoulou, Z., Karlos, S., Tsoumakas, G.: ETHOS: an online hate speech detection dataset. arXiv preprint arXiv:2006.08328 (2020)"},{"issue":"4","key":"24_CR23","doi-asserted-by":"publisher","first-page":"3005","DOI":"10.1007\/S10462-022-10246-W","volume":"56","author":"E Mosqueira-Rey","year":"2023","unstructured":"Mosqueira-Rey, E., Hern\u00e1ndez-Pereira, E., Alonso-R\u00edos, D., Bobes-Bascar\u00e1n, J., Fern\u00e1ndez-Leal, \u00c1.: Human-in-the-loop machine learning: a state of the art. Artif. Intell. Rev. 56(4), 3005\u20133054 (2023). https:\/\/doi.org\/10.1007\/S10462-022-10246-W","journal-title":"Artif. Intell. Rev."},{"key":"24_CR24","doi-asserted-by":"crossref","unstructured":"Rahman, S., Kandogan, E.: Characterizing practices, limitations, and opportunities related to text information extraction workflows: a human-in-the-loop perspective. In: Proceedings of the 2022 CHI Conference on Human Factors in Computing Systems, pp. 1\u201315 (2022)","DOI":"10.1145\/3491102.3502068"},{"key":"24_CR25","doi-asserted-by":"crossref","unstructured":"Reiss, M.V.: Testing the reliability of chatGPT for text annotation and classification: a cautionary remark. arXiv preprint arXiv:2304.11085 (2023)","DOI":"10.31219\/osf.io\/rvy5p"},{"key":"24_CR26","unstructured":"Rouzegar, H., Makrehchi, M.: Enhancing text classification through LLM-driven active learning and human annotation. arXiv preprint arXiv:2406.12114 (2024)"},{"key":"24_CR27","unstructured":"Salimans, T., Zhang, H., Radford, A., Metaxas, D.: Improving GANs using optimal transport. arXiv preprint arXiv:1803.05573 (2018)"},{"key":"24_CR28","unstructured":"Schr\u00f6der, C., Niekler, A.: A survey of active learning for text classification using deep neural networks. arXiv preprint arXiv:2008.07267 (2020)"},{"key":"24_CR29","doi-asserted-by":"crossref","unstructured":"Shmueli, B., Fell, J., Ray, S., Ku, L.W.: Beyond fair pay: ethical implications of NLP crowdsourcing. arXiv preprint arXiv:2104.10097 (2021)","DOI":"10.18653\/v1\/2021.naacl-main.295"},{"key":"24_CR30","unstructured":"T\u00f6rnberg, P.: ChatGPT-4 outperforms experts and crowd workers in annotating political twitter messages with zero-shot learning. arXiv preprint arXiv:2304.06588 (2023)"},{"key":"24_CR31","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.119446","volume":"216","author":"G del Valle-Cano","year":"2023","unstructured":"del Valle-Cano, G., Quijano-S\u00e1nchez, L., Liberatore, F., G\u00f3mez, J.: SocialHaterBERT: a dichotomous approach for automatically detecting hate speech on twitter through textual analysis and user profiles. Expert Syst. Appl. 216, 119446 (2023)","journal-title":"Expert Syst. Appl."},{"key":"24_CR32","unstructured":"Zhang, X., Zhao, J., LeCun, Y.: Character-level convolutional networks for text classification. Adv. Neural Inf. Process. Syst. 28 (2015)"},{"key":"24_CR33","unstructured":"Zhu, Y., Zhang, P., Haq, E.U., Hui, P., Tyson, G.: Can chatGPT reproduce human-generated labels? A study of social computing tasks. arXiv preprint arXiv:2304.10145 (2023)"}],"container-title":["Lecture Notes in Computer Science","Knowledge Science, Engineering and Management"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-3055-7_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T04:07:38Z","timestamp":1763006858000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-3055-7_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,14]]},"ISBN":["9789819530540","9789819530557"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-3055-7_24","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,14]]},"assertion":[{"value":"14 November 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"KSEM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Knowledge Science, Engineering and Management","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Macao","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 August 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 August 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ksem2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ksem2025.scimeeting.cn\/en\/web\/index\/27434","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}