{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T19:35:29Z","timestamp":1743017729862,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":28,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819620531"},{"type":"electronic","value":"9789819620548"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-981-96-2054-8_19","type":"book-chapter","created":{"date-parts":[[2025,1,2]],"date-time":"2025-01-02T15:48:43Z","timestamp":1735832923000},"page":"249-262","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Data-Free Functional Projection of\u00a0Large Language Models onto Social Media Tagging Domain"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-2395-9731","authenticated-orcid":false,"given":"Wenchuan","family":"Mu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4569-0901","authenticated-orcid":false,"given":"Kwan Hui","family":"Lim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,1,3]]},"reference":[{"key":"19_CR1","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., et al.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877\u20131901 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"19_CR2","doi-asserted-by":"publisher","unstructured":"Cho, J.H., Hariharan, B.: On the efficacy of knowledge distillation. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 4793\u20134801 (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00489","DOI":"10.1109\/ICCV.2019.00489"},{"key":"19_CR3","doi-asserted-by":"publisher","unstructured":"Demszky, D., Movshovitz-Attias, D., Ko, J., Cowen, A., Nemade, G., Ravi, S.: GoEmotions: a dataset of fine-grained emotions. In: Jurafsky, D., Chai, J., Schluter, N., Tetreault, J. (eds.) Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 4040\u20134054. Association for Computational Linguistics, Online (2020). https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.372. https:\/\/aclanthology.org\/2020.acl-main.372","DOI":"10.18653\/v1\/2020.acl-main.372"},{"key":"19_CR4","doi-asserted-by":"publisher","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Burstein, J., Doran, C., Solorio, T. (eds.) Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pp. 4171\u20134186. Association for Computational Linguistics, Minneapolis, Minnesota (2019). https:\/\/doi.org\/10.18653\/v1\/N19-1423. https:\/\/aclanthology.org\/N19-1423","DOI":"10.18653\/v1\/N19-1423"},{"key":"19_CR5","unstructured":"Duan, J., et\u00a0al.: Efficient training of large language models on distributed infrastructures: a survey. arXiv preprint arXiv:2407.20018 (2024)"},{"issue":"6","key":"19_CR6","doi-asserted-by":"publisher","first-page":"1789","DOI":"10.1007\/s11263-021-01453-z","volume":"129","author":"J Gou","year":"2021","unstructured":"Gou, J., Yu, B., Maybank, S.J., Tao, D.: Knowledge distillation: a survey. Int. J. Comput. Vision 129(6), 1789\u20131819 (2021). https:\/\/doi.org\/10.1007\/s11263-021-01453-z","journal-title":"Int. J. Comput. Vision"},{"key":"19_CR7","unstructured":"Kaplan, J., et al.: Scaling laws for neural language models (2020)"},{"key":"19_CR8","doi-asserted-by":"publisher","unstructured":"Kim, D., et al.: SOLAR 10.7b: scaling large language models with simple yet effective depth up-scaling (2023). https:\/\/doi.org\/10.48550\/ARXIV.2312.15166","DOI":"10.48550\/ARXIV.2312.15166"},{"key":"19_CR9","doi-asserted-by":"publisher","unstructured":"Kim, Y., Rush, A.M.: Sequence-level knowledge distillation. In: Su, J., Duh, K., Carreras, X. (eds.) Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pp. 1317\u20131327. Association for Computational Linguistics, Austin, Texas (2016). https:\/\/doi.org\/10.18653\/v1\/D16-1139. https:\/\/aclanthology.org\/D16-1139","DOI":"10.18653\/v1\/D16-1139"},{"key":"19_CR10","unstructured":"Kreyszig, E.: Introductory Functional Analysis with Applications, Wiley Classics Library, vol.\u00a017. Wiley India Pvt. Limited (2007). https:\/\/books.google.com.sg\/books?id=osXw-pRsptoC"},{"key":"19_CR11","doi-asserted-by":"publisher","unstructured":"Li, C., Ge, Y., Mao, J., Li, D., Shan, Y.: Taggpt: large language models are zero-shot multimodal taggers (2023). https:\/\/doi.org\/10.48550\/ARXIV.2304.03022","DOI":"10.48550\/ARXIV.2304.03022"},{"key":"19_CR12","doi-asserted-by":"publisher","unstructured":"Li, Z., Zhu, H., Lu, Z., Yin, M.: Synthetic data generation with large language models for text classification: Potential and limitations. In: Bouamor, H., Pino, J., Bali, K. (eds.) Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pp. 10443\u201310461. Association for Computational Linguistics, Singapore (2023). https:\/\/doi.org\/10.18653\/v1\/2023.emnlp-main.647. https:\/\/aclanthology.org\/2023.emnlp-main.647","DOI":"10.18653\/v1\/2023.emnlp-main.647"},{"key":"19_CR13","unstructured":"Liu, Y., et al.: Roberta: a robustly optimized BERT pretraining approach (2019)"},{"key":"19_CR14","unstructured":"Liu, Z., Sun, M., Zhou, T., Huang, G., Darrell, T.: Rethinking the value of network pruning. In: 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, 6\u20139 May 2019. OpenReview.net (2019). https:\/\/openreview.net\/forum?id=rJlnB3C5Ym"},{"key":"19_CR15","unstructured":"Maas, A.L., Daly, R.E., Pham, P.T., Huang, D., Ng, A.Y., Potts, C.: Learning word vectors for sentiment analysis. In: Lin, D., Matsumoto, Y., Mihalcea, R. (eds.) Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, pp. 142\u2013150. Association for Computational Linguistics, Portland, Oregon, USA (2011). https:\/\/aclanthology.org\/P11-1015"},{"issue":"8","key":"19_CR16","first-page":"9","volume":"1","author":"A Radford","year":"2019","unstructured":"Radford, A., et al.: Language models are unsupervised multitask learners. OpenAI Blog 1(8), 9 (2019)","journal-title":"OpenAI Blog"},{"key":"19_CR17","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer (2019)"},{"key":"19_CR18","unstructured":"Rudin, W.: Principles of Mathematical Analysis. International series in pure and applied mathematics, McGraw-Hill (1976). https:\/\/books.google.com.sg\/books?id=kwqzPAAACAAJ"},{"key":"19_CR19","unstructured":"Sanh, V., Debut, L., Chaumond, J., Wolf, T.: Distilbert, a distilled version of BERT: smaller, faster, cheaper and lighter (2019)"},{"key":"19_CR20","doi-asserted-by":"publisher","unstructured":"See, A., Liu, P.J., Manning, C.D.: Get to the point: summarization with pointer-generator networks. In: Barzilay, R., Kan, M.Y. (eds.) Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 1073\u20131083. Association for Computational Linguistics, Vancouver, Canada (2017). https:\/\/doi.org\/10.18653\/v1\/P17-1099. https:\/\/aclanthology.org\/P17-1099","DOI":"10.18653\/v1\/P17-1099"},{"key":"19_CR21","doi-asserted-by":"publisher","unstructured":"Touvron, H., et\u00a0al.: Llama 2: open foundation and fine-tuned chat models (2023). https:\/\/doi.org\/10.48550\/ARXIV.2307.09288","DOI":"10.48550\/ARXIV.2307.09288"},{"key":"19_CR22","doi-asserted-by":"publisher","unstructured":"Tunstall, L., et al.: Zephyr: direct distillation of LM alignment (2023). https:\/\/doi.org\/10.48550\/ARXIV.2310.16944","DOI":"10.48550\/ARXIV.2310.16944"},{"key":"19_CR23","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Guyon, I., et al. (eds.) Advances in Neural Information Processing Systems, vol.\u00a030. Curran Associates, Inc. (2017). https:\/\/proceedings.neurips.cc\/paper\/2017\/file\/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf"},{"key":"19_CR24","doi-asserted-by":"publisher","unstructured":"Wold, S., Esbensen, K., Geladi, P.: Principal component analysis. Chemometrics Intell. Lab. Syst. 2(1), 37\u201352 (1987). https:\/\/doi.org\/10.1016\/0169-7439(87)80084-9. Proceedings of the Multivariate Statistical Workshop for Geologists and Geochemists","DOI":"10.1016\/0169-7439(87)80084-9"},{"key":"19_CR25","doi-asserted-by":"publisher","unstructured":"Yu, M., Huang, Q., Qin, H., Scheele, C., Yang, C.: Deep learning for real-time social media text classification for situation awareness\u2013using hurricanes sandy, harvey, and irma as case studies. In: Li, Z., Huang, Q., Emrich, C.T. (eds.) Social Sensing and Big Data Computing for Disaster Management, pp. 33\u201350. Routledge (2020). https:\/\/doi.org\/10.4324\/9781003106494","DOI":"10.4324\/9781003106494"},{"key":"19_CR26","unstructured":"Zhang, X., Zhao, J., LeCun, Y.: Character-level convolutional networks for text classification. In: Cortes, C., Lawrence, N., Lee, D., Sugiyama, M., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol.\u00a028. Curran Associates, Inc. (2015). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2015\/file\/250cf8b51c773f3f8dc8b4be867a9a02-Paper.pdf"},{"key":"19_CR27","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.120327","volume":"227","author":"T Zhou","year":"2023","unstructured":"Zhou, T., Chiam, K.H.: Synthetic data generation method for data-free knowledge distillation in regression neural networks. Expert Syst. Appl. 227, 120327 (2023). https:\/\/doi.org\/10.1016\/j.eswa.2023.120327","journal-title":"Expert Syst. Appl."},{"key":"19_CR28","unstructured":"Zhu, M., Gupta, S.: To prune, or not to prune: exploring the efficacy of pruning for model compression. In: 6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, April 30 - May 3, 2018, Workshop Track Proceedings. OpenReview.net (2018). https:\/\/openreview.net\/forum?id=Sy1iIDkPM"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-2054-8_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,23]],"date-time":"2025-03-23T01:42:24Z","timestamp":1742694144000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-2054-8_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819620531","9789819620548"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-2054-8_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"3 January 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Nara","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","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":"9 January 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 January 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/mmm2025.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}