{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,18]],"date-time":"2026-01-18T13:29:05Z","timestamp":1768742945322,"version":"3.49.0"},"reference-count":89,"publisher":"Springer Science and Business Media LLC","issue":"7-8","license":[{"start":{"date-parts":[[2025,2,27]],"date-time":"2025-02-27T00:00:00Z","timestamp":1740614400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,2,27]],"date-time":"2025-02-27T00:00:00Z","timestamp":1740614400000},"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":["Int. J. Mach. Learn. &amp; Cyber."],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1007\/s13042-025-02548-6","type":"journal-article","created":{"date-parts":[[2025,2,27]],"date-time":"2025-02-27T03:53:37Z","timestamp":1740628417000},"page":"4879-4898","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["MixPro: Simple yet Effective Data Augmentation for Prompt-based Learning"],"prefix":"10.1007","volume":"16","author":[{"given":"Bohan","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Longxu","family":"Dou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yutai","family":"Hou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunlong","family":"Feng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Honglin","family":"Mu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Enbo","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qingfu","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qinghua","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wanxiang","family":"Che","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,2,27]]},"reference":[{"key":"2548_CR1","doi-asserted-by":"crossref","unstructured":"Schick T, Sch\u00fctze H (2021) It\u2019s not just size that matters: Small language models are also few-shot learners. In: Proceedings of ACL, pp. 2339\u20132352","DOI":"10.18653\/v1\/2021.naacl-main.185"},{"key":"2548_CR2","unstructured":"Liu P, Yuan W, Fu J, Jiang Z, Hayashi H, Neubig G (2021) Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing. arXiv:2107.13586"},{"key":"2548_CR3","unstructured":"Brown TB, Mann B, Ryder N, Subbiah M, Kaplan J (2020) Language models are few-shot learners. arXiv:2005.14165"},{"key":"2548_CR4","doi-asserted-by":"crossref","unstructured":"Gao T, Fisch A, Chen D (2021) Making pre-trained language models better few-shot learners. In: Proceedings of ACL, pp. 3816\u20133830","DOI":"10.18653\/v1\/2021.acl-long.295"},{"key":"2548_CR5","doi-asserted-by":"crossref","unstructured":"Seoh R, Birle I, Tak M, Chang H-S, Pinette B, Hough A (2021) Open aspect target sentiment classification with natural language prompts. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 6311\u20136322. Association for Computational Linguistics, Online and Punta Cana, Dominican Republic","DOI":"10.18653\/v1\/2021.emnlp-main.509"},{"key":"2548_CR6","doi-asserted-by":"crossref","unstructured":"Qi K, Wan H, Du J, Chen H (2022) Enhancing cross-lingual natural language inference by prompt-learning from cross-lingual templates. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 1910\u20131923. Association for Computational Linguistics, Dublin, Ireland","DOI":"10.18653\/v1\/2022.acl-long.134"},{"key":"2548_CR7","doi-asserted-by":"crossref","unstructured":"Zhong R, Lee K, Zhang Z, Klein D (2021) Adapting language models for zero-shot learning by meta-tuning on dataset and prompt collections. Findings of the Association for Computational Linguistics: EMNLP (2021) Punta Cana. Dominican Republic, Association for Computational Linguistics, pp 2856\u20132878","DOI":"10.18653\/v1\/2021.findings-emnlp.244"},{"key":"2548_CR8","doi-asserted-by":"publisher","first-page":"414","DOI":"10.1162\/tacl_a_00468","volume":"10","author":"E Ben-David","year":"2022","unstructured":"Ben-David E, Oved N, Reichart R (2022) PADA: Example-based Prompt Learning for on-the-fly Adaptation to Unseen Domains. Trans Assoc Comput Linguist 10:414\u2013433","journal-title":"Trans Assoc Comput Linguist"},{"key":"2548_CR9","doi-asserted-by":"crossref","unstructured":"Clark C, Lee K, Chang M-W, Kwiatkowski T, Collins M, Toutanova K (2019) BoolQ: Exploring the surprising difficulty of natural yes\/no questions. In: Proceedings of ACL, pp. 2924\u20132936","DOI":"10.18653\/v1\/N19-1300"},{"key":"2548_CR10","doi-asserted-by":"crossref","unstructured":"van\u00a0de Kar M, Xia M, Chen D, Artetxe M (2022) Don\u2019t prompt, search! mining-based zero-shot learning with language models. In: Conference on Empirical Methods in Natural Language Processing","DOI":"10.18653\/v1\/2022.emnlp-main.509"},{"key":"2548_CR11","doi-asserted-by":"crossref","unstructured":"Cao B, Lin H, Han X, Liu F, Sun L (2022) Can prompt probe pretrained language models? understanding the invisible risks from a causal view. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 5796\u20135808. Association for Computational Linguistics, Dublin, Ireland","DOI":"10.18653\/v1\/2022.acl-long.398"},{"key":"2548_CR12","doi-asserted-by":"crossref","unstructured":"Ren S, Zhang J, Li L, Sun X, Zhou J (2021) Text AutoAugment: Learning compositional augmentation policy for text classification. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 9029\u20139043. Association for Computational Linguistics, Online and Punta Cana, Dominican Republic","DOI":"10.18653\/v1\/2021.emnlp-main.711"},{"key":"2548_CR13","unstructured":"Chen X, Li L, Zhang N, Liang X, Deng S, Tan C, Huang F, Si L, Chen H (2022) Decoupling knowledge from memorization: Retrieval-augmented prompt learning. arXiv:2205.14704"},{"key":"2548_CR14","doi-asserted-by":"crossref","unstructured":"Simard PY, LeCun Y, Denker JS, Victorri B (2000) Transformation invariance in pattern recognition: Tangent distance and propagation. Int J Imaging Syst Technol 11","DOI":"10.1002\/1098-1098(2000)11:3<181::AID-IMA1003>3.0.CO;2-E"},{"key":"2548_CR15","first-page":"1","volume":"2015","author":"C Szegedy","year":"2014","unstructured":"Szegedy C, Liu W, Jia Y, Sermanet P, Reed SE, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2014) Going deeper with convolutions. IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2015:1\u20139","journal-title":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"2548_CR16","doi-asserted-by":"crossref","unstructured":"Wei J, Zou K (2019) EDA: Easy data augmentation techniques for boosting performance on text classification tasks. In: Proceedings of EMNLP, pp. 6382\u20136388","DOI":"10.18653\/v1\/D19-1670"},{"key":"2548_CR17","doi-asserted-by":"crossref","unstructured":"Li B, Hou Y, Che W (2022) Data augmentation approaches in natural language processing: A survey. AI Open","DOI":"10.1016\/j.aiopen.2022.03.001"},{"key":"2548_CR18","unstructured":"Hu Z, Tan B, Salakhutdinov R, Mitchell TM, Xing EP (2019) Learning data manipulation for augmentation and weighting. arXiv:1910.12795"},{"key":"2548_CR19","doi-asserted-by":"crossref","unstructured":"Anaby-Tavor A, Carmeli B, Goldbraich E, Kantor A, Kour G, Shlomov S, Tepper N, Zwerdling N (2020) Do not have enough data? deep learning to the rescue! In: Proceedings of AAAI, pp. 7383\u20137390","DOI":"10.1609\/aaai.v34i05.6233"},{"key":"2548_CR20","unstructured":"Chen J, Tam D, Raffel C, Bansal M, Yang D (2021) An empirical survey of data augmentation for limited data learning in nlp. arXiv:2106.07499"},{"key":"2548_CR21","unstructured":"Chapelle O, Weston J, Bottou L, Vapnik V (2000) Vicinal risk minimization. Adv Neural Inf Process Syst 13"},{"key":"2548_CR22","doi-asserted-by":"crossref","unstructured":"Zhang H, Ciss\u00e9 M, Dauphin Y, Lopez-Paz D (2017) mixup: Beyond empirical risk minimization. arXiv:1710.09412","DOI":"10.1007\/978-1-4899-7687-1_79"},{"key":"2548_CR23","unstructured":"de Marneffe M-C, Simons M, Tonhauser J (2019) The commitmentbank: Investigating projection in naturally occurring discourse"},{"key":"2548_CR24","first-page":"177","volume":"3944","author":"I Dagan","year":"2005","unstructured":"Dagan I, Glickman O, Magnini B (2005) The PASCAL recognising textual entailment challenge. Mach Learn Challenges 3944:177\u2013190","journal-title":"Mach Learn Challenges"},{"key":"2548_CR25","unstructured":"Bar-Haim R, Dagan I, Dolan B, Ferro L, Giampiccolo D, Magnini B (2006) The second pascal recognising textual entailment challenge"},{"key":"2548_CR26","unstructured":"Guo H, Mao Y, Zhang R (2019) Augmenting data with mixup for sentence classification: An empirical study. arXiv:1905.08941"},{"key":"2548_CR27","unstructured":"Lan Z, Chen M, Goodman S, Gimpel K, Sharma P, Soricut R (2019) Albert: A lite bert for self-supervised learning of language representations. arXiv:1909.11942"},{"key":"2548_CR28","unstructured":"He P, Liu X, Gao J, Chen W (2020) Deberta: Decoding-enhanced bert with disentangled attention. arXiv:2006.03654"},{"issue":"10","key":"2548_CR29","doi-asserted-by":"publisher","first-page":"4361","DOI":"10.1007\/s13042-023-01898-3","volume":"14","author":"L Dou","year":"2023","unstructured":"Dou L, Gao Y, Pan M, Wang D, Che W, Zhan D, Lou J-G (2023) Unisar: A unified structure-aware autoregressive language model for text-to-sql. Int J Mach Learn Cybernet 14(10):4361\u20134376","journal-title":"Int J Mach Learn Cybernet"},{"key":"2548_CR30","unstructured":"Dubey A, Jauhri A, Pandey A, Kadian A, Al-Dahle A (2024) The llama 3 herd of models. arXiv:2407.21783"},{"key":"2548_CR31","unstructured":"Anil R, Dai AM, Firat O, Johnson M, Lepikhin D (2023) Palm 2 technical report. arXiv:2305.10403"},{"key":"2548_CR32","doi-asserted-by":"crossref","unstructured":"Yuan S, Chen J, Fu Z, Ge X, Shah S, Jankowski CR, Yang D, Xiao Y (2023) Distilling script knowledge from large language models for constrained language planning. In: Annual Meeting of the Association for Computational Linguistics","DOI":"10.18653\/v1\/2023.acl-long.236"},{"issue":"10","key":"2548_CR33","doi-asserted-by":"publisher","first-page":"3409","DOI":"10.1007\/s13042-022-01604-9","volume":"13","author":"Y Hou","year":"2022","unstructured":"Hou Y, Mao J, Lai Y, Chen C, Che W, Chen Z, Liu T (2022) Fewjoint: A few-shot learning benchmark for joint language understanding. Int J Mach Learn Cybernet 13(10):3409\u20133423","journal-title":"Int J Mach Learn Cybernet"},{"key":"2548_CR34","doi-asserted-by":"crossref","unstructured":"Cohan A, Ammar W, van Zuylen M, Cady F (2019) Structural scaffolds for citation intent classification in scientific publications. arXiv:1904.01608","DOI":"10.18653\/v1\/N19-1361"},{"key":"2548_CR35","doi-asserted-by":"crossref","unstructured":"Wang B, Zhao Y, Lu X, Qin B (2023) Cognitive distortion based explainable depression detection and analysis technologies for the adolescent internet users on social media. Front Public Health 10","DOI":"10.3389\/fpubh.2022.1045777"},{"key":"2548_CR36","unstructured":"Dernoncourt F, Lee JY (2017) Pubmed 200k rct: a dataset for sequential sentence classification in medical abstracts. In: International Joint Conference on Natural Language Processing"},{"key":"2548_CR37","doi-asserted-by":"publisher","first-page":"438","DOI":"10.1007\/s41666-023-00155-0","volume":"8","author":"C Shyr","year":"2023","unstructured":"Shyr C, Hu Y, Harris PA, Xu H (2023) Identifying and extracting rare diseases and their phenotypes with large language models. J Healthcare Inf Res 8:438\u2013461","journal-title":"J Healthcare Inf Res"},{"key":"2548_CR38","unstructured":"Zhao J, Guan Z, Zhao W, Jiang Y, He X (2023) Few-shot domain adaptation for charge prediction on unprofessional descriptions. arXiv:2309.17313"},{"key":"2548_CR39","unstructured":"Yang AM, Xiao B, Wang B, Zhang B, Bian C (2023) Baichuan 2: Open large-scale language models. arXiv:2309.10305"},{"key":"2548_CR40","doi-asserted-by":"crossref","unstructured":"Glaser I, Sadegharmaki S, Komboz B, Matthes F (2021) Data scarcity: Methods to improve the quality of text classification. In: International Conference on Pattern Recognition Applications and Methods","DOI":"10.5220\/0010268005560564"},{"key":"2548_CR41","unstructured":"Devlin J, Chang M-W, Lee K, Toutanova K (2019) Bert: Pre-training of deep bidirectional transformers for language understanding. In: North American Chapter of the Association for Computational Linguistics"},{"key":"2548_CR42","unstructured":"Li X, Xue J-T, Xie Z, Li M (2023) Think outside the code: Brainstorming boosts large language models in code generation. arXiv:2305.10679"},{"key":"2548_CR43","doi-asserted-by":"publisher","first-page":"5328","DOI":"10.1109\/TKDE.2023.3332787","volume":"36","author":"Y Zhu","year":"2022","unstructured":"Zhu Y, Zhou X, Qiang J, Li Y, Yuan Y, Wu X (2022) Prompt-learning for short text classification. IEEE Trans Knowl Data Eng 36:5328\u20135339","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"2548_CR44","doi-asserted-by":"crossref","unstructured":"Taylor N, Zhang Y, Joyce DW, Gao Z, Kormilitzin A, Nevado-Holgado AJ (2023) Clinical prompt learning with frozen language models. IEEE Trans Neural Netw Learn Syst PP","DOI":"10.1109\/TNNLS.2023.3294633"},{"key":"2548_CR45","doi-asserted-by":"crossref","unstructured":"Schick T, Sch\u00fctze H (2021) Exploiting cloze-questions for few-shot text classification and natural language inference. In: Proceedings of ACL, pp. 255\u2013269","DOI":"10.18653\/v1\/2021.eacl-main.20"},{"key":"2548_CR46","unstructured":"Nie F, Chen M, Zhang Z, Cheng X (2022) Improving few-shot performance of language models via nearest neighbor calibration. arXiv:2212.02216"},{"key":"2548_CR47","doi-asserted-by":"crossref","unstructured":"Cheng Y, Jiang L, Macherey W, Eisenstein J (2020) AdvAug: Robust adversarial augmentation for neural machine translation. In: Proceedings of ACL, pp. 5961\u20135970","DOI":"10.18653\/v1\/2020.acl-main.529"},{"key":"2548_CR48","unstructured":"Hendrycks D, Mu N, Cubuk ED, Zoph B, Gilmer J, Lakshminarayanan B (2020) Augmix: A simple data processing method to improve robustness and uncertainty. In: Proceedings of ICLR"},{"key":"2548_CR49","first-page":"140","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 PJ (2020) Exploring the limits of transfer learning with a unified text-to-text transformer. J Mach Learn Res 21:140\u2013114067","journal-title":"J Mach Learn Res"},{"key":"2548_CR50","doi-asserted-by":"crossref","unstructured":"Zhou J, Zheng Y, Tang J, Li J, Yang Z (2021) FlipDA: Effective and Robust Data Augmentation for Few-Shot Learning","DOI":"10.18653\/v1\/2022.acl-long.592"},{"key":"2548_CR51","unstructured":"Wang A, Pruksachatkun Y, Nangia N, Singh A, Michael J, Hill F, Levy O, Bowman SR (2019) Superglue: A stickier benchmark for general-purpose language understanding systems. In: Proceedings of NeurIPS, pp. 3261\u20133275"},{"key":"2548_CR52","doi-asserted-by":"crossref","unstructured":"Khashabi D, Chaturvedi S, Roth M, Upadhyay S, Roth D (2018) Looking beyond the surface: A challenge set for reading comprehension over multiple sentences. In: Proceedings of ACL, pp. 252\u2013262","DOI":"10.18653\/v1\/N18-1023"},{"key":"2548_CR53","unstructured":"Levesque HJ, Davis E, Morgenstern L (2012) The winograd schema challenge. In: Principles of Knowledge Representation and Reasoning: Proceedings of the Thirteenth International Conference"},{"key":"2548_CR54","doi-asserted-by":"crossref","unstructured":"Pilehvar MT, Camacho-Collados J (2019) WiC: the word-in-context dataset for evaluating context-sensitive meaning representations. In: Proceedings of ACL, pp. 1267\u20131273","DOI":"10.18653\/v1\/N19-1128"},{"key":"2548_CR55","unstructured":"Zhang S, Liu X, Liu J, Gao J, Duh K, Durme BV (2018) Record: Bridging the gap between human and machine commonsense reading comprehension. arXiv:1810.12885"},{"key":"2548_CR56","unstructured":"Roemmele M, Bejan CA, Gordon AS (2011) Choice of plausible alternatives: An evaluation of commonsense causal reasoning. In: Logical Formalizations of Commonsense Reasoning"},{"key":"2548_CR57","unstructured":"Zhang X, Zhao JJ, LeCun Y (2015) Character-level convolutional networks for text classification. In: Proceedings of NeurIPS, pp. 649\u2013657"},{"issue":"11","key":"2548_CR58","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1145\/219717.219748","volume":"38","author":"GA Miller","year":"1995","unstructured":"Miller GA (1995) Wordnet: a lexical database for english. Commun ACM 38(11):39\u201341","journal-title":"Commun ACM"},{"key":"2548_CR59","doi-asserted-by":"crossref","unstructured":"Wang WY, Yang D (2015) That\u2019s so annoying!!!: A lexical and frame-semantic embedding based data augmentation approach to automatic categorization of annoying behaviors using #petpeeve tweets. In: Proceedings of EMNLP, pp. 2557\u20132563","DOI":"10.18653\/v1\/D15-1306"},{"key":"2548_CR60","doi-asserted-by":"crossref","unstructured":"Pennington J, Socher R, Manning C (2014) GloVe: Global vectors for word representation. In: Proceedings of EMNLP, pp. 1532\u20131543","DOI":"10.3115\/v1\/D14-1162"},{"key":"2548_CR61","unstructured":"Xie Q, Dai Z, Hovy EH, Luong T, Le Q (2020) Unsupervised data augmentation for consistency training. In: Proceedings of NeurIPS"},{"key":"2548_CR62","doi-asserted-by":"crossref","unstructured":"Jiao X, Yin Y, Shang L, Jiang X, Chen X, Li L, Wang F, Liu Q (2020) TinyBERT: Distilling BERT for natural language understanding. In: Proceedings of ACL, pp. 4163\u20134174","DOI":"10.18653\/v1\/2020.findings-emnlp.372"},{"key":"2548_CR63","unstructured":"Dodge J, Ilharco G, Schwartz R, Farhadi A, Hajishirzi H, Smith NA (2020) Fine-tuning pretrained language models: Weight initializations, data orders, and early stopping. arXiv:2002.06305"},{"key":"2548_CR64","doi-asserted-by":"crossref","unstructured":"Petroni F, Rockt\u00e4schel T, Riedel S, Lewis P, Bakhtin A, Wu Y, Miller A (2019) Language models as knowledge bases? In: Proceedings of EMNLP, pp. 2463\u20132473","DOI":"10.18653\/v1\/D19-1250"},{"key":"2548_CR65","doi-asserted-by":"crossref","unstructured":"Schick T, Sch\u00fctze H (2020) Few-Shot Text Generation with Pattern-Exploiting Training","DOI":"10.18653\/v1\/2021.emnlp-main.32"},{"key":"2548_CR66","first-page":"423","volume":"8","author":"Z Jiang","year":"2020","unstructured":"Jiang Z, Xu FF, Araki J, Neubig G (2020) How can we know what language models know? Trans Assoc Comput Lingu 8:423\u2013438","journal-title":"Trans Assoc Comput Lingu"},{"key":"2548_CR67","unstructured":"Yuan W, Neubig G, Liu P (2021) BARTScore: Evaluating Generated Text as Text Generation"},{"key":"2548_CR68","doi-asserted-by":"crossref","unstructured":"Haviv A, Berant J, Globerson A (2021) BERTese: Learning to speak to BERT. In: Proceedings of ACL, pp. 3618\u20133623","DOI":"10.18653\/v1\/2021.eacl-main.316"},{"key":"2548_CR69","doi-asserted-by":"crossref","unstructured":"Wallace E, Feng S, Kandpal N, Gardner M, Singh S (2019) Universal adversarial triggers for attacking and analyzing NLP. In: Proceedings of EMNLP, pp. 2153\u20132162","DOI":"10.18653\/v1\/D19-1221"},{"key":"2548_CR70","doi-asserted-by":"crossref","unstructured":"Shin T, Razeghi Y, Logan\u00a0IV RL, Wallace E, Singh S (2020) AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts. In: Proceedings of EMNLP, pp. 4222\u20134235","DOI":"10.18653\/v1\/2020.emnlp-main.346"},{"key":"2548_CR71","doi-asserted-by":"crossref","unstructured":"Davison J, Feldman J, Rush A (2019) Commonsense knowledge mining from pretrained models. In: Proceedings of EMNLP, pp. 1173\u20131178","DOI":"10.18653\/v1\/D19-1109"},{"key":"2548_CR72","unstructured":"Li XL, Liang P (2021) Prefix-tuning: Optimizing continuous prompts for generation. In: Proceedings of ACL, pp. 4582\u20134597"},{"key":"2548_CR73","doi-asserted-by":"crossref","unstructured":"Lester B, Al-Rfou R, Constant N (2021) The Power of Scale for Parameter-Efficient Prompt Tuning","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"2548_CR74","unstructured":"Tsimpoukelli M, Menick J, Cabi S, Eslami SMA, Vinyals O, Hill F (2021) Multimodal few-shot learning with frozen language models. arXiv:2106.13884"},{"key":"2548_CR75","doi-asserted-by":"crossref","unstructured":"Zhong Z, Friedman D, Chen D (2021) Factual probing is [MASK]: Learning vs. learning to recall. In: Proceedings of ACL, pp. 5017\u20135033","DOI":"10.18653\/v1\/2021.naacl-main.398"},{"key":"2548_CR76","doi-asserted-by":"crossref","unstructured":"Qin G, Eisner J (2021) Learning how to ask: Querying LMs with mixtures of soft prompts. In: Proceedings of ACL, pp. 5203\u20135212","DOI":"10.18653\/v1\/2021.naacl-main.410"},{"key":"2548_CR77","doi-asserted-by":"crossref","unstructured":"Hambardzumyan K, Khachatrian H, May J (2021) WARP: Word-level Adversarial ReProgramming. In: Proceedings of ACL, pp. 4921\u20134933","DOI":"10.18653\/v1\/2021.acl-long.381"},{"key":"2548_CR78","unstructured":"Liu X, Zheng Y, Du Z, Ding M, Qian Y, Yang Z, Tang J. (2021) GPT understands, too. arXiv:2103.10385"},{"key":"2548_CR79","doi-asserted-by":"crossref","unstructured":"Han X, Zhao W, Ding N, Liu Z, Sun M (2021) PTR: Prompt Tuning with Rules for Text Classification","DOI":"10.1016\/j.aiopen.2022.11.003"},{"key":"2548_CR80","unstructured":"Wen Y, Jain N, Kirchenbauer J, Goldblum M, Geiping J, Goldstein T (2023) Hard prompts made easy: Gradient-based discrete optimization for prompt tuning and discovery. arXiv:2302.03668"},{"issue":"10","key":"2548_CR81","doi-asserted-by":"publisher","first-page":"3621","DOI":"10.1007\/s13042-023-01854-1","volume":"14","author":"B Zheng","year":"2023","unstructured":"Zheng B, Che W (2023) Improving cross-lingual language understanding with consistency regularization-based fine-tuning. Int J Mach Learn Cybernet 14(10):3621\u20133639","journal-title":"Int J Mach Learn Cybernet"},{"key":"2548_CR82","doi-asserted-by":"crossref","unstructured":"Chen C, Shu K (2022) Promptda: Label-guided data augmentation for prompt-based few shot learners. arXiv:2205.09229","DOI":"10.18653\/v1\/2023.eacl-main.41"},{"key":"2548_CR83","doi-asserted-by":"crossref","unstructured":"Chowdhury JR, Zhuang Y, Wang S (2022) Novelty controlled paraphrase generation with retrieval augmented conditional prompt tuning. In: AAAI Conference on Artificial Intelligence","DOI":"10.1609\/aaai.v36i10.21297"},{"key":"2548_CR84","doi-asserted-by":"crossref","unstructured":"Wang Y, Xu C, Sun Q, Hu H, Tao C, Geng X, Jiang D (2022) Promda: Prompt-based data augmentation for low-resource nlu tasks. In: Annual Meeting of the Association for Computational Linguistics","DOI":"10.18653\/v1\/2022.acl-long.292"},{"key":"2548_CR85","unstructured":"Chen M, Papangelis A, Tao C, Rosenbaum A, Kim S, Liu Y, Yu Z, Hakkani-T\u00fcr DZ (2022) Weakly supervised data augmentation through prompting for dialogue understanding. arXiv:2210.14169"},{"key":"2548_CR86","doi-asserted-by":"crossref","unstructured":"Cai D, Wu Y, Yuan H, Wang S, Lin FX, Xu M (2022) Aug-fedprompt: Practical few-shot federated nlp with data-augmented prompts. arXiv:2212.00192","DOI":"10.1145\/3578356.3592575"},{"issue":"8","key":"2548_CR87","first-page":"9","volume":"1","author":"A Radford","year":"2019","unstructured":"Radford A, Wu J, Child R, Luan D, Amodei D, Sutskever I (2019) Language models are unsupervised multitask learners. OpenAI blog 1(8):9","journal-title":"OpenAI blog"},{"key":"2548_CR88","doi-asserted-by":"crossref","unstructured":"Lewis M, Liu Y, Goyal N, Ghazvininejad M, Mohamed A-R, Levy O, Stoyanov V, Zettlemoyer L (2019) Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. In: Annual Meeting of the Association for Computational Linguistics","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"2548_CR89","unstructured":"Rosset C, Xiong C, Phan MH, Song X, Bennett P, Tiwary S (2020) Knowledge-aware language model pretraining. arXiv:2007.00655"}],"container-title":["International Journal of Machine Learning and Cybernetics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-025-02548-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s13042-025-02548-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-025-02548-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T07:05:45Z","timestamp":1757142345000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s13042-025-02548-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,27]]},"references-count":89,"journal-issue":{"issue":"7-8","published-print":{"date-parts":[[2025,8]]}},"alternative-id":["2548"],"URL":"https:\/\/doi.org\/10.1007\/s13042-025-02548-6","relation":{},"ISSN":["1868-8071","1868-808X"],"issn-type":[{"value":"1868-8071","type":"print"},{"value":"1868-808X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2,27]]},"assertion":[{"value":"12 November 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 January 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 February 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}