{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,11]],"date-time":"2026-01-11T01:27:07Z","timestamp":1768094827327,"version":"3.49.0"},"publisher-location":"Berlin, Heidelberg","reference-count":53,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783662722428","type":"print"},{"value":"9783662722435","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,10,4]],"date-time":"2025-10-04T00:00:00Z","timestamp":1759536000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,4]],"date-time":"2025-10-04T00:00:00Z","timestamp":1759536000000},"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\/978-3-662-72243-5_5","type":"book-chapter","created":{"date-parts":[[2025,10,3]],"date-time":"2025-10-03T12:13:44Z","timestamp":1759493624000},"page":"77-94","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Task Prompt Vectors: Effective Initialization Through Multi-task Soft Prompt Transfer"],"prefix":"10.1007","author":[{"given":"Robert","family":"Belanec","sequence":"first","affiliation":[]},{"given":"Simon","family":"Ostermann","sequence":"additional","affiliation":[]},{"given":"Ivan","family":"Srba","sequence":"additional","affiliation":[]},{"given":"Maria","family":"Bielikova","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,10,4]]},"reference":[{"key":"5_CR1","doi-asserted-by":"publisher","unstructured":"Asai, A., Salehi, M., Peters, M., Hajishirzi, H.: ATTEMPT: parameter-efficient multi-task tuning via attentional mixtures of soft prompts. In: Goldberg, Y., Kozareva, Z., Zhang, Y. (eds.) Proceedings of the 2022 Conference on EMNLP, pp. 6655\u20136672. ACL, Abu Dhabi (2022). https:\/\/doi.org\/10.18653\/v1\/2022.emnlp-main.446","DOI":"10.18653\/v1\/2022.emnlp-main.446"},{"key":"5_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"722","DOI":"10.1007\/978-3-540-76298-0_52","volume-title":"The Semantic Web","author":"S Auer","year":"2007","unstructured":"Auer, S., Bizer, C., Kobilarov, G., Lehmann, J., Cyganiak, R., Ives, Z.: DBpedia: a nucleus for a web of open data. In: Aberer, K., et al. (eds.) ISWC ASWC 2007. LNCS, vol. 4825, pp. 722\u2013735. Springer, Heidelberg (2007). https:\/\/doi.org\/10.1007\/978-3-540-76298-0_52"},{"key":"5_CR3","unstructured":"Bi, X., et\u00a0al.: DeepSeek LLM: scaling open-source language models with longtermism. arXiv preprint arXiv:2401.02954 (2024)"},{"key":"5_CR4","doi-asserted-by":"crossref","unstructured":"Bowman, S.R., Angeli, G., Potts, C., Manning, C.D.: A large annotated corpus for learning natural language inference. In: Proceedings of the 2015 Conference on EMNLP (EMNLP). ACL (2015)","DOI":"10.18653\/v1\/D15-1075"},{"key":"5_CR5","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":"5_CR6","doi-asserted-by":"publisher","unstructured":"Cer, D., Diab, M., Agirre, E., Lopez-Gazpio, I., Specia, L.: SemEval-2017 task 1: semantic textual similarity multilingual and crosslingual focused evaluation. In: Bethard, S., Carpuat, M., Apidianaki, M., Mohammad, S.M., Cer, D., Jurgens, D. (eds.) Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017), pp. 1\u201314. ACL, Vancouver (2017). https:\/\/doi.org\/10.18653\/v1\/S17-2001","DOI":"10.18653\/v1\/S17-2001"},{"key":"5_CR7","doi-asserted-by":"crossref","unstructured":"Chronopoulou, A., Pfeiffer, J., Maynez, J., Wang, X., Ruder, S., Agrawal, P.: Language and task arithmetic with parameter-efficient layers for zero-shot summarization. arXiv preprint arXiv:2311.09344 (2023)","DOI":"10.18653\/v1\/2024.mrl-1.7"},{"key":"5_CR8","unstructured":"Costa-Juss\u00e0, M.R., et\u00a0al.: No language left behind: scaling human-centered machine translation. arXiv preprint arXiv:2207.04672 (2022)"},{"key":"5_CR9","doi-asserted-by":"crossref","unstructured":"Davari, M., Belilovsky, E.: Model breadcrumbs: scaling multi-task model merging with sparse masks (2023). arXiv:2312.06795 [cs]","DOI":"10.1007\/978-3-031-73226-3_16"},{"key":"5_CR10","unstructured":"Dolan, W.B., Brockett, C.: Automatically constructing a corpus of sentential paraphrases. In: Proceedings of the International Workshop on Paraphrasing (2005)"},{"key":"5_CR11","unstructured":"Dubey, A., et\u00a0al.: The LLaMA 3 herd of models. arXiv preprint arXiv:2407.21783 (2024)"},{"issue":"287","key":"5_CR12","doi-asserted-by":"publisher","first-page":"613","DOI":"10.1080\/01621459.1959.10501524","volume":"54","author":"OJ Dunn","year":"1959","unstructured":"Dunn, O.J.: Confidence intervals for the means of dependent, normally distributed variables. J. Am. Stat. Assoc. 54(287), 613\u2013621 (1959)","journal-title":"J. Am. Stat. Assoc."},{"key":"5_CR13","unstructured":"Fourrier, C., Habib, N., Wolf, T., Tunstall, L.: LightEval: a lightweight framework for LLM evaluation (2023). https:\/\/github.com\/huggingface\/lighteval"},{"key":"5_CR14","unstructured":"Frankle, J., Dziugaite, G.K., Roy, D., Carbin, M.: Linear mode connectivity and the lottery ticket hypothesis. In: ICML, pp. 3259\u20133269. PMLR (2020)"},{"key":"5_CR15","doi-asserted-by":"publisher","unstructured":"Gu, Y., Han, X., Liu, Z., Huang, M.: PPT: pre-trained prompt tuning for few-shot learning. In: Muresan, S., Nakov, P., Villavicencio, A. (eds.) Proceedings of the 60th Annual Meeting of the ACL (Volume 1: Long Papers), pp. 8410\u20138423. ACL, Dublin (2022). https:\/\/doi.org\/10.18653\/v1\/2022.acl-long.576","DOI":"10.18653\/v1\/2022.acl-long.576"},{"key":"5_CR16","doi-asserted-by":"crossref","unstructured":"Gurgurov, D., Vykopal, I., van Genabith, J., Ostermann, S.: Small models, big impact: efficient corpus and graph-based adaptation of small multilingual language models for low-resource languages. arXiv preprint arXiv:2502.10140 (2025)","DOI":"10.18653\/v1\/2025.acl-srw.24"},{"key":"5_CR17","unstructured":"Houlsby, N., et al.: Parameter-efficient transfer learning for NLP. In: ICML, pp. 2790\u20132799. PMLR (2019)"},{"key":"5_CR18","doi-asserted-by":"crossref","unstructured":"Hovy, E., Gerber, L., Hermjakob, U., Lin, C.Y., Ravichandran, D.: Toward semantics-based answer pinpointing. In: Proceedings of the First International Conference on Human Language Technology Research (2001)","DOI":"10.3115\/1072133.1072221"},{"key":"5_CR19","unstructured":"Hu, E.J., et al.: LoRA: low-rank adaptation of large language models. In: ICLR (2022). https:\/\/openreview.net\/forum?id=nZeVKeeFYf9"},{"key":"5_CR20","unstructured":"Ilharco, G., Ribeiro, M.T., Wortsman, M., Schmidt, L., Hajishirzi, H., Farhadi, A.: Editing models with task arithmetic. In: The Eleventh ICLR (2022)"},{"key":"5_CR21","doi-asserted-by":"crossref","unstructured":"Khot, T., Sabharwal, A., Clark, P.: SciTaiL: a textual entailment dataset from science question answering. In: AAAI Conference on Artificial Intelligence (2018). https:\/\/api.semanticscholar.org\/CorpusID:24462950","DOI":"10.1609\/aaai.v32i1.12022"},{"key":"5_CR22","unstructured":"Klimaszewski, M., Andruszkiewicz, P., Birch, A.: No train but gain: language arithmetic for training-free language adapters enhancement. arXiv preprint arXiv:2404.15737 (2024)"},{"key":"5_CR23","doi-asserted-by":"publisher","unstructured":"Lee, H., Jeong, M., Yun, S.Y., Kim, K.E.: Bayesian multi-task transfer learning for soft prompt tuning. In: Bouamor, H., Pino, J., Bali, K. (eds.) Findings of the ACL: EMNLP 2023, pp. 4942\u20134958. ACL, Singapore (2023). https:\/\/doi.org\/10.18653\/v1\/2023.findings-emnlp.329","DOI":"10.18653\/v1\/2023.findings-emnlp.329"},{"key":"5_CR24","doi-asserted-by":"publisher","unstructured":"Lester, B., Al-Rfou, R., Constant, N.: The power of scale for parameter-efficient prompt tuning. In: Moens, M.F., Huang, X., Specia, L., Yih, S.W.T. (eds.) Proceedings of the 2021 Conference on EMNLP, pp. 3045\u20133059. ACL, Online and Punta Cana (2021). https:\/\/doi.org\/10.18653\/v1\/2021.emnlp-main.243","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"5_CR25","unstructured":"Li, M., et al.: Branch-train-merge: embarrassingly parallel training of expert language models (2022). arXiv:2208.03306 [cs]"},{"key":"5_CR26","doi-asserted-by":"publisher","unstructured":"Li, X.L., Liang, P.: Prefix-tuning: Optimizing continuous prompts for generation. In: Zong, C., Xia, F., Li, W., Navigli, R. (eds.) Proceedings of the 59th Annual Meeting of the ACL and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pp. 4582\u20134597. ACL, Online (2021). https:\/\/doi.org\/10.18653\/v1\/2021.acl-long.353","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"5_CR27","doi-asserted-by":"crossref","unstructured":"Li, X., Roth, D.: Learning question classifiers. In: COLING 2002: The 19th International Conference on Computational Linguistics (2002)","DOI":"10.3115\/1072228.1072378"},{"key":"5_CR28","doi-asserted-by":"crossref","unstructured":"Liu, X., et al.: GPT understands, too. AI Open (2023)","DOI":"10.1016\/j.aiopen.2023.08.012"},{"key":"5_CR29","unstructured":"Liu, Y., et al.: RoBERTa: a robustly optimized BERT pretraining approach. arXiv preprint arXiv:1907.11692 (2019)"},{"key":"5_CR30","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 ACL: Human Language Technologies, pp. 142\u2013150. ACL, Portland (2011)"},{"key":"5_CR31","unstructured":"Matena, M., Raffel, C.: Merging models with fisher-weighted averaging (2022). arXiv:2111.09832 [cs]"},{"key":"5_CR32","unstructured":"Ortiz-Jimenez, G., Favero, A., Frossard, P.: Task arithmetic in the tangent space: improved editing of pre-trained models. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"5_CR33","unstructured":"Pecher, B., Srba, I., Bielikova, M.: Comparing specialised small and general large language models on text classification: 100 labelled samples to achieve break-even performance. arXiv preprint arXiv:2402.12819 (2024)"},{"key":"5_CR34","doi-asserted-by":"publisher","unstructured":"Pfeiffer, J., Kamath, A., R\u00fcckl\u00e9, A., Cho, K., Gurevych, I.: AdapterFusion: non-destructive task composition for transfer learning. In: Merlo, P., Tiedemann, J., Tsarfaty, R. (eds.) Proceedings of the 16th Conference of the European Chapter of the ACL: Main Volume, pp. 487\u2013503. ACL, Online (2021). https:\/\/doi.org\/10.18653\/v1\/2021.eacl-main.39","DOI":"10.18653\/v1\/2021.eacl-main.39"},{"key":"5_CR35","doi-asserted-by":"publisher","unstructured":"Qin, Y., et al.: Exploring universal intrinsic task subspace for few-shot learning via prompt tuning. IEEE\/ACM Trans. Audio, Speech and Lang. Process. 32, 3631\u20133643 (2024). https:\/\/doi.org\/10.1109\/TASLP.2024.3430545","DOI":"10.1109\/TASLP.2024.3430545"},{"issue":"8","key":"5_CR36","first-page":"9","volume":"1","author":"A Radford","year":"2019","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I., et al.: Language models are unsupervised multitask learners. OpenAI blog 1(8), 9 (2019)","journal-title":"OpenAI blog"},{"issue":"140","key":"5_CR37","first-page":"1","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., Zhou, Y., Li, W., Liu, P.J.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21(140), 1\u201367 (2020)","journal-title":"J. Mach. Learn. Res."},{"key":"5_CR38","doi-asserted-by":"publisher","unstructured":"Rajpurkar, P., Jia, R., Liang, P.: Know what you don\u2019t know: unanswerable questions for SQuAD. In: Gurevych, I., Miyao, Y. (eds.) Proceedings of the 56th Annual Meeting of the ACL (Volume 2: Short Papers), pp. 784\u2013789. ACL, Melbourne (2018). https:\/\/doi.org\/10.18653\/v1\/P18-2124","DOI":"10.18653\/v1\/P18-2124"},{"key":"5_CR39","unstructured":"Ram\u00e9, A., Ahuja, K., Zhang, J., Cord, M., Bottou, L., Lopez-Paz, D.: Model ratatouille: recycling diverse models for out-of-distribution generalization. In: ICML, pp. 28656\u201328679. PMLR (2023)"},{"key":"5_CR40","unstructured":"Shi, Z., Lipani, A.: DePT: decomposed prompt tuning for parameter-efficient fine-tuning. In: The Twelfth ICLR (2024). https:\/\/openreview.net\/forum?id=KjegfPGRde"},{"key":"5_CR41","doi-asserted-by":"crossref","unstructured":"Socher, R., et al.: Recursive deep models for semantic compositionality over a sentiment treebank. In: Proceedings of the 2013 Conference on EMNLP, pp. 1631\u20131642 (2013)","DOI":"10.18653\/v1\/D13-1170"},{"key":"5_CR42","unstructured":"Stoica, G., Bolya, D., Bjorner, J., Ramesh, P., Hearn, T., Hoffman, J.: ZipIt! Merging models from different tasks without training (2024). arXiv:2305.03053 [cs]"},{"key":"5_CR43","doi-asserted-by":"crossref","unstructured":"Student: The probable error of a mean. Biometrika 1\u201325 (1908)","DOI":"10.2307\/2331554"},{"key":"5_CR44","doi-asserted-by":"publisher","unstructured":"Su, Y., et al.: On transferability of prompt tuning for natural language processing. In: Carpuat, M., de\u00a0Marneffe, M.C., Meza\u00a0Ruiz, I.V. (eds.) Proceedings of the 2022 Conference of the North American Chapter of the ACL: Human Language Technologies, pp. 3949\u20133969. ACL, Seattle (2022). https:\/\/doi.org\/10.18653\/v1\/2022.naacl-main.290","DOI":"10.18653\/v1\/2022.naacl-main.290"},{"key":"5_CR45","doi-asserted-by":"publisher","unstructured":"Vu, T., Lester, B., Constant, N., Al-Rfou\u2019, R., Cer, D.: SPoT: better frozen model adaptation through soft prompt transfer. In: Muresan, S., Nakov, P., Villavicencio, A. (eds.) Proceedings of the 60th Annual Meeting of the ACL (Volume 1: Long Papers), pp. 5039\u20135059. ACL, Dublin, Ireland (2022). https:\/\/doi.org\/10.18653\/v1\/2022.acl-long.346","DOI":"10.18653\/v1\/2022.acl-long.346"},{"key":"5_CR46","doi-asserted-by":"publisher","unstructured":"Wang, A., Singh, A., Michael, J., Hill, F., Levy, O., Bowman, S.: GLUE: a multi-task benchmark and analysis platform for natural language understanding. In: Linzen, T., Chrupa\u0142a, G., Alishahi, A. (eds.) Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, pp. 353\u2013355. ACL, Brussels (2018). https:\/\/doi.org\/10.18653\/v1\/W18-5446","DOI":"10.18653\/v1\/W18-5446"},{"key":"5_CR47","unstructured":"Wang, Z., Panda, R., Karlinsky, L., Feris, R., Sun, H., Kim, Y.: Multitask prompt tuning enables parameter-efficient transfer learning. In: The Eleventh ICLR (2023). https:\/\/openreview.net\/forum?id=Nk2pDtuhTq"},{"key":"5_CR48","doi-asserted-by":"publisher","first-page":"625","DOI":"10.1162\/tacl_a_00290","volume":"7","author":"A Warstadt","year":"2019","unstructured":"Warstadt, A., Singh, A., Bowman, S.R.: Neural network acceptability judgments. Trans. ACL 7, 625\u2013641 (2019). https:\/\/doi.org\/10.1162\/tacl_a_00290","journal-title":"Trans. ACL"},{"key":"5_CR49","doi-asserted-by":"publisher","unstructured":"Williams, A., Nangia, N., Bowman, S.: A broad-coverage challenge corpus for sentence understanding through inference. In: Walker, M., Ji, H., Stent, A. (eds.) Proceedings of the 2018 Conference of the North American Chapter of the ACL: Human Language Technologies, Volume 1 (Long Papers), pp. 1112\u20131122. ACL, New Orleans (2018). https:\/\/doi.org\/10.18653\/v1\/N18-1101","DOI":"10.18653\/v1\/N18-1101"},{"key":"5_CR50","doi-asserted-by":"crossref","unstructured":"Wortsman, M., et\u00a0al.: Robust fine-tuning of zero-shot models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7959\u20137971 (2022)","DOI":"10.1109\/CVPR52688.2022.00780"},{"key":"5_CR51","unstructured":"Xu, L., Xie, H., Qin, S.Z.J., Tao, X., Wang, F.L.: Parameter-efficient fine-tuning methods for pretrained language models: a critical review and assessment. arXiv preprint arXiv:2312.12148 (2023)"},{"key":"5_CR52","first-page":"12589","volume":"36","author":"J Zhang","year":"2023","unstructured":"Zhang, J., Liu, J., He, J., et al.: Composing parameter-efficient modules with arithmetic operation. Adv. Neural. Inf. Process. Syst. 36, 12589\u201312610 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"5_CR53","unstructured":"Zhang, X., Zhao, J., LeCun, Y.: Character-level convolutional networks for text classification. Adv. Neural. Inf. Process. Syst. 28 (2015)"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases. Research Track and Applied Data Science Track"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-662-72243-5_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,3]],"date-time":"2025-10-03T12:14:07Z","timestamp":1759493647000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-662-72243-5_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,4]]},"ISBN":["9783662722428","9783662722435"],"references-count":53,"URL":"https:\/\/doi.org\/10.1007\/978-3-662-72243-5_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,4]]},"assertion":[{"value":"4 October 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"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":"Porto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Portugal","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":"15 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ecmlpkdd.org\/2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}