{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T18:55:28Z","timestamp":1757616928769,"version":"3.44.0"},"publisher-location":"Cham","reference-count":45,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031703706"},{"type":"electronic","value":"9783031703713"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-70371-3_13","type":"book-chapter","created":{"date-parts":[[2024,8,31]],"date-time":"2024-08-31T23:31:13Z","timestamp":1725147073000},"page":"218-234","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Harnessing the\u00a0Power of\u00a0Prompt Experts: Efficient Knowledge Distillation for\u00a0Enhanced Language Understanding"],"prefix":"10.1007","author":[{"given":"Xv","family":"Meng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Rao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuhan","family":"Qi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,8,22]]},"reference":[{"key":"13_CR1","unstructured":"Asif, U., Tang, J., Harrer, S.: Ensemble knowledge distillation for learning improved and efficient networks. In: Proceedings of European Conference on Artificial Intelligence (2019)"},{"key":"13_CR2","unstructured":"Brown, T.B., et al.: Language models are few-shot learners. In: Proceedings of Conference on Neural Information Processing Systems (2020)"},{"key":"13_CR3","doi-asserted-by":"crossref","unstructured":"Chen, X., Su, J., Zhang, J.: A two-teacher framework for knowledge distillation. In: Proceedings of International Symposium on Neural Networks (2019)","DOI":"10.1007\/978-3-030-22796-8_7"},{"key":"13_CR4","doi-asserted-by":"crossref","unstructured":"Chen, Y., He, L.: SKD-NER: continual named entity recognition via span-based knowledge distillation with reinforcement learning. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pp. 6689\u20136700 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.413"},{"key":"13_CR5","doi-asserted-by":"crossref","unstructured":"Dan, Y., Zhou, J., Chen, Q., Bai, Q., He, L.: Enhancing class understanding via prompt-tuning for zero-shot text classification. In: Proceedings of International Conference on Acoustics, Speech and Signal Processing, pp. 4303\u20134307 (2022)","DOI":"10.1109\/ICASSP43922.2022.9746200"},{"key":"13_CR6","doi-asserted-by":"crossref","unstructured":"Fukuda, T., Suzuki, M., Kurata, G., Thomas, S., Cui, J., Ramabhadran, B.: Efficient knowledge distillation from an ensemble of teachers. In: Proceedings of Interspeech (2017)","DOI":"10.21437\/Interspeech.2017-614"},{"key":"13_CR7","doi-asserted-by":"crossref","unstructured":"Gu, Y., Han, X., Liu, Z., Huang, M.: PPT: pre-trained prompt tuning for few-shot learning. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics, pp. 8410\u20138423 (2022)","DOI":"10.18653\/v1\/2022.acl-long.576"},{"key":"13_CR8","doi-asserted-by":"crossref","unstructured":"Guo, M., Guo, M., Dougherty, E., Jin, F.: MSQ-BioBERT: ambiguity resolution to enhance BioBERT medical question-answering. In: Proceedings of the ACM Web Conference (2023)","DOI":"10.1145\/3543507.3583878"},{"key":"13_CR9","unstructured":"Hendrycks, D., Gimpel, K.: A baseline for detecting misclassified and out-of-distribution examples in neural networks. arXiv preprint arXiv:1610.02136 (2016)"},{"key":"13_CR10","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. In: Conference on Neural Information Processing Systems (2015)"},{"key":"13_CR11","doi-asserted-by":"crossref","unstructured":"Hou, B., Wang, C., Chen, X., Qiu, M., Feng, L., Huang, J.: Prompt-distiller: few-shot knowledge distillation for prompt-based language learners with dual contrastive learning. In: Proceedings of International Conference on Acoustics, Speech and Signal Processing (2023)","DOI":"10.1109\/ICASSP49357.2023.10095721"},{"key":"13_CR12","doi-asserted-by":"crossref","unstructured":"Iovine, A., Fang, A., Fetahu, B., Rokhlenko, O., Malmasi, S.: Cyclener: an unsupervised training approach for named entity recognition. In: Proceedings of the ACM Web Conference (2022)","DOI":"10.1145\/3485447.3512012"},{"key":"13_CR13","doi-asserted-by":"crossref","unstructured":"Jiang, W., Mao, Q., Li, J., Lin, C., Yang, W., Deng, T., Wang, Z.: Disco: distilled student models co-training for semi-supervised text mining. In: Conference on Empirical Methods in Natural Language Processing (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.244"},{"key":"13_CR14","doi-asserted-by":"crossref","unstructured":"Jiang, Y., Chan, C., Chen, M., Wang, W.: Lion: adversarial distillation of proprietary large language models. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pp. 3134\u20133154 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.189"},{"key":"13_CR15","doi-asserted-by":"crossref","unstructured":"Lee, S.H., Kim, D.H., Song, B.C.: Self-supervised knowledge distillation using singular value decomposition. In: Proceedings of European Conference on Computer Vision (2018)","DOI":"10.1007\/978-3-030-01231-1_21"},{"key":"13_CR16","doi-asserted-by":"crossref","unstructured":"Li, H., Yang, L., Li, L., Xu, C., Xia, S.T., Yuan, C.: PTS: a prompt-based teacher-student network for weakly supervised aspect detection. In: Proceedings of International Joint Conference on Neural Networks (2022)","DOI":"10.1109\/IJCNN55064.2022.9892147"},{"key":"13_CR17","doi-asserted-by":"crossref","unstructured":"Li, L., Zhang, Z., Bao, R., Harimoto, K., Sun, X.: Distributional correlation-aware knowledge distillation for stock trading volume prediction. In: Proceedings of ECML PKDD (2022)","DOI":"10.1007\/978-3-031-26422-1_7"},{"key":"13_CR18","doi-asserted-by":"crossref","unstructured":"Li, X.L., Liang, P.: Prefix-tuning: optimizing continuous prompts for generation. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (2021)","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"13_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1007\/978-3-030-58610-2_2","volume-title":"Computer Vision \u2013 ECCV 2020","author":"X Li","year":"2020","unstructured":"Li, X., Wu, J., Fang, H., Liao, Y., Wang, F., Qian, C.: Local correlation consistency for knowledge distillation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12357, pp. 18\u201333. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58610-2_2"},{"key":"13_CR20","first-page":"1","volume":"55","author":"P Liu","year":"2021","unstructured":"Liu, P., Yuan, W., Fu, J., Jiang, Z., Hayashi, H., Neubig, G.: Pre-train, prompt, and predict: a systematic survey of prompting methods in natural language processing. ACM Comput. Surv. 55, 1\u201335 (2021)","journal-title":"ACM Comput. Surv."},{"key":"13_CR21","doi-asserted-by":"crossref","unstructured":"Liu, X., et al.: P-tuning v2: prompt tuning can be comparable to fine-tuning universally across scales and tasks. In: Proceedings of the 60th Annual Meeting of the Association of Computational Linguistics (2022)","DOI":"10.18653\/v1\/2022.acl-short.8"},{"key":"13_CR22","doi-asserted-by":"crossref","unstructured":"Miao, Z., et al.: Exploring all-in-one knowledge distillation framework for neural machine translation. In: Proceedings of the 2023 Conference on EMNLP, pp. 2929\u20132940 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.178"},{"key":"13_CR23","unstructured":"Niemann, O., Vox, C., Werner, T.: Towards comparable knowledge distillation in semantic image segmentation. In: Proceedings of ECML PKDD (2023)"},{"key":"13_CR24","doi-asserted-by":"crossref","unstructured":"Park, W., Kim, D., Lu, Y., Cho, M.: Relational knowledge distillation. In: Proceedings of the Conference on Computer Vision and Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.00409"},{"key":"13_CR25","doi-asserted-by":"crossref","unstructured":"Passalis, N., Tefas, A.: Learning deep representations with probabilistic knowledge transfer. In: Proceedings of the European Conference on Computer Vision (2018)","DOI":"10.1007\/978-3-030-01252-6_17"},{"issue":"6","key":"13_CR26","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2023.103510","volume":"60","author":"S Qi","year":"2023","unstructured":"Qi, S., Cao, Z., Rao, J., Wang, L., Xiao, J., Wang, X.: What is the limitation of multimodal LLMs? A deeper look into multimodal LLMs through prompt probing. Inf. Process. Manag. 60(6), 103510 (2023)","journal-title":"Inf. Process. Manag."},{"key":"13_CR27","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21 (2019)"},{"key":"13_CR28","doi-asserted-by":"publisher","unstructured":"Rao, J., et al.: Dynamic contrastive distillation for image-text retrieval. IEEE Trans. Multimed. 1\u201313 (2023). https:\/\/doi.org\/10.1109\/TMM.2023.3236837","DOI":"10.1109\/TMM.2023.3236837"},{"key":"13_CR29","doi-asserted-by":"crossref","unstructured":"Rao, J., Meng, X., Ding, L., Qi, S., Tao, D.: Parameter-efficient and student-friendly knowledge distillation. IEEE Trans. Multimed. (2023)","DOI":"10.1109\/TMM.2023.3321480"},{"key":"13_CR30","doi-asserted-by":"crossref","unstructured":"Rao, J., Qian, T., Qi, S., Wu, Y., Liao, Q., Wang, X.: Student can also be a good teacher: extracting knowledge from vision-and-language model for cross-modal retrieval. In: CIKM (2021)","DOI":"10.1145\/3459637.3482194"},{"key":"13_CR31","doi-asserted-by":"crossref","unstructured":"Rao, J., et al.: Where does the performance improvement come from - a reproducibility concern about image-text retrieval. In: SIGIR (2022)","DOI":"10.1145\/3477495.3531715"},{"key":"13_CR32","doi-asserted-by":"crossref","unstructured":"Sahu, G., Vechtomova, O., Bahdanau, D., Laradji, I.: PromptMix: a class boundary augmentation method for large language model distillation. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pp. 5316\u20135327 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.323"},{"key":"13_CR33","doi-asserted-by":"crossref","unstructured":"Schick, T., Sch\u00fctze, H.: Exploiting cloze-questions for few-shot text classification and natural language inference. In: Proceedings of the Conference of the European Chapter of the Association for Computational Linguistics, pp. 255\u2013269 (2021)","DOI":"10.18653\/v1\/2021.eacl-main.20"},{"key":"13_CR34","doi-asserted-by":"crossref","unstructured":"Shin, T., Razeghi, Y., Logan\u00a0IV, R.L., Wallace, E., Singh, S.: AutoPrompt: eliciting knowledge from language models with automatically generated prompts. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing, pp. 4222\u20134235 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.346"},{"key":"13_CR35","doi-asserted-by":"crossref","unstructured":"Tjong Kim\u00a0Sang, E.F., De\u00a0Meulder, F.: Introduction to the conll-2003 shared task: language-independent named entity recognition. ArXiv cs.CL\/0306050 (2003)","DOI":"10.3115\/1119176.1119195"},{"key":"13_CR36","unstructured":"Wang, A., et al.: Superglue: a stickier benchmark for general-purpose language understanding systems. In: Proceedings of Conference on Neural Information Processing Systems (2019)"},{"key":"13_CR37","doi-asserted-by":"crossref","unstructured":"Wang, L., Lu, H.: Classification of histopathologic images of breast cancer by multi-teacher small-sample knowledge distillation. In: Proceedings of International Conference on Artificial Intelligence and Computer Engineering, pp. 642\u2013647 (2021)","DOI":"10.1109\/ICAICE54393.2021.00127"},{"key":"13_CR38","doi-asserted-by":"crossref","unstructured":"Wang, S., Chen, X., Kou, M., Shi, J.: Prue: distilling knowledge from sparse teacher networks. In: Proceedings of ECML PKDD (2022)","DOI":"10.1007\/978-3-031-26409-2_7"},{"key":"13_CR39","doi-asserted-by":"crossref","unstructured":"Wen, H., Song, X., Yin, J., Wu, J., Guan, W., Nie, L.: Self-training boosted multi-factor matching network for composed image retrieval. IEEE Trans. Pattern Anal. Mach. Intell. (2023)","DOI":"10.1109\/TPAMI.2023.3346434"},{"key":"13_CR40","doi-asserted-by":"crossref","unstructured":"Wu, M.C., Chiu, C.T., Wu, K.H.: Multi-teacher knowledge distillation for compressed video action recognition on deep neural networks. In: Proceedings of International Conference on Acoustics, Speech and Signal Processing, pp. 2202\u20132206 (2019)","DOI":"10.1109\/ICASSP.2019.8682450"},{"key":"13_CR41","doi-asserted-by":"crossref","unstructured":"Yang, Z., Shou, L., Gong, M., Lin, W., Jiang, D.: Model compression with two-stage multi-teacher knowledge distillation for web question answering system. In: Proceedings of the 13th International Conference on Web Search and Data Mining (2019)","DOI":"10.1145\/3336191.3371792"},{"key":"13_CR42","doi-asserted-by":"crossref","unstructured":"Yi, J., Yang, D., Yuan, S., Cao, K., Zhang, Z., Xiao, Y.: Contextual information and commonsense based prompt for emotion recognition in conversation. In: Proceedings of ECML PKDD, pp. 707\u2013723 (2022)","DOI":"10.1007\/978-3-031-26390-3_41"},{"key":"13_CR43","doi-asserted-by":"crossref","unstructured":"You, S., Xu, C., Xu, C., Tao, D.: Learning from multiple teacher networks. In: Proceedings of the 23rd ACM SIGKDD International Conference (2017)","DOI":"10.1145\/3097983.3098135"},{"key":"13_CR44","doi-asserted-by":"crossref","unstructured":"Yu, P., Wang, W., Li, C., Zhang, R., Jin, Z., Chen, C.: STT: soft template tuning for few-shot adaptation. In: Proceedings of International Conference on Data Mining Workshops, pp. 941\u2013946 (2022)","DOI":"10.1109\/ICDMW58026.2022.00122"},{"key":"13_CR45","unstructured":"Yuan, F., et al.: Reinforced multi-teacher selection for knowledge distillation. In: Proceedings of AAAI Conference on Artificial Intelligence (2020)"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases. Research Track and Demo Track"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-70371-3_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,5]],"date-time":"2025-09-05T21:04:43Z","timestamp":1757106283000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-70371-3_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031703706","9783031703713"],"references-count":45,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-70371-3_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"22 August 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"ECML PKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vilnius","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lithuania","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2024.ecmlpkdd.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}