{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T16:48:09Z","timestamp":1783788489798,"version":"3.55.0"},"reference-count":68,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"National Key R&D Program of China","award":["2020AAA0106502"],"award-info":[{"award-number":["2020AAA0106502"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/taslp.2024.3430545","type":"journal-article","created":{"date-parts":[[2024,7,18]],"date-time":"2024-07-18T17:40:46Z","timestamp":1721324446000},"page":"3631-3643","source":"Crossref","is-referenced-by-count":10,"title":["Exploring Universal Intrinsic Task Subspace for Few-Shot Learning via Prompt Tuning"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3608-5061","authenticated-orcid":false,"given":"Yujia","family":"Qin","sequence":"first","affiliation":[{"name":"Department of Computer Science, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5727-143X","authenticated-orcid":false,"given":"Xiaozhi","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9509-9573","authenticated-orcid":false,"given":"Yusheng","family":"Su","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0151-6178","authenticated-orcid":false,"given":"Yankai","family":"Lin","sequence":"additional","affiliation":[{"name":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8758-9484","authenticated-orcid":false,"given":"Ning","family":"Ding","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7424-9605","authenticated-orcid":false,"given":"Jing","family":"Yi","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-5882-8870","authenticated-orcid":false,"given":"Weize","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7709-2543","authenticated-orcid":false,"given":"Zhiyuan","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6244-0664","authenticated-orcid":false,"given":"Juanzi","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8907-3526","authenticated-orcid":false,"given":"Lei","family":"Hou","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1374-5979","authenticated-orcid":false,"given":"Peng","family":"Li","sequence":"additional","affiliation":[{"name":"Institute for AI Industry Research (AIR), Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maosong","family":"Sun","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5899-5165","authenticated-orcid":false,"given":"Jie","family":"Zhou","sequence":"additional","affiliation":[{"name":"Pattern Recognition Center, WeChat AI, Tencent Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Computat. Linguistics: Hum. Lang. Technol.","author":"Devlin","year":"2019"},{"key":"ref2","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"key":"ref3","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","author":"Raffel","year":"2019"},{"key":"ref4","doi-asserted-by":"crossref","DOI":"10.1016\/j.aiopen.2021.08.002","article-title":"Pre-trained models: Past, present and future","author":"Han","year":"2021"},{"key":"ref5","article-title":"Recent advances in natural language processing via large pre-trained language models: A survey","author":"Min","year":"2021"},{"key":"ref6","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2021.emnlp-main.243","article-title":"The power of scale for parameter-efficient prompt tuning","author":"Lester","year":"2021"},{"key":"ref7","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Houlsby","year":"2019"},{"key":"ref8","first-page":"7319","article-title":"Intrinsic dimensionality explains the effectiveness of language model fine-tuning","volume-title":"Proc. 59th Annu. Meeting Assoc. Comput. Linguistics 11th Int. Joint Conf. Natural Lang. Process.","author":"Aghajanyan","year":"2021"},{"key":"ref9","first-page":"4582","article-title":"Prefix-tuning: Optimizing continuous prompts for generation","volume-title":"Proc. 59th Annu. Meeting Assoc. Comput. Linguistics 11th Int. Joint Conf. Natural Lang. Process.","author":"Li","year":"2021"},{"key":"ref10","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst. 33: Annu. Conf. Neural Inf. Process. Syst.","author":"Brown","year":"2020"},{"key":"ref11","first-page":"255","article-title":"Exploiting cloze-questions for few-shot text classification and natural language inference","volume-title":"Proc. 16th Conf. Eur. Chapter Assoc. Comput. Linguistics: Main Volume","author":"Schick","year":"2021"},{"key":"ref12","first-page":"2339","article-title":"Its not just size that matters: Small language models are also few-shot learners","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics: Hum. Lang. Technol.","author":"Schick","year":"2021"},{"key":"ref13","first-page":"423","article-title":"How can we know what language models know?","volume-title":"Trans. Assoc. Comput. Linguistics","volume":"8","author":"Jiang","year":"2020"},{"key":"ref14","first-page":"4222","article-title":"AutoPrompt: Eliciting knowledge from language models with automatically generated prompts","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Shin","year":"2020"},{"key":"ref15","first-page":"3816","article-title":"Making pre-trained language models better few-shot learners","volume-title":"Proc. 59th Annu. Meeting Assoc. Comput. Linguistics 11th Int. Joint Conf. Natural Lang. Process.","author":"Gao","year":"2021"},{"key":"ref16","first-page":"4921","article-title":"WARP: Word-level adversarial ReProgramming","volume-title":"Proc. 59th Annu. Meeting Assoc. Comput. Linguistics 11th Int. Joint Conf. Natural Lang. Process.","author":"Hambardzumyan","year":"2021"},{"key":"ref17","first-page":"5017","article-title":"Factual probing is [MASK]: Learning vs learning to recall","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics: Hum. Lang. Technol.","author":"Zhong","year":"2021"},{"key":"ref18","first-page":"5203","article-title":"Learning how to ask: Querying LMs with mixtures of soft prompts","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics: Hum. Lang. Technol.","author":"Qin","year":"2021"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.346"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.758"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.576"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.290"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.37"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.87"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.258"},{"key":"ref26","first-page":"1950","article-title":"Few-shot parameter-efficient fine-tuning is better and cheaper than in-context learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu","year":"2022"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-naacl.3"},{"key":"ref28","article-title":"Measuring the intrinsic dimension of objective landscapes","volume-title":"Proc. 6th Int. Conf. Learn. Representations","author":"Li","year":"2018"},{"key":"ref29","article-title":"The intrinsic dimension of images and its impact on learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Pope","year":"2020"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00411"},{"key":"ref31","article-title":"Intrinsic dimension of data representations in deep neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ansuini","year":"2019"},{"key":"ref32","first-page":"6776","article-title":"Intrinsic dimension, persistent homology and generalization in neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Birdal","year":"2021"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2015.08.029"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2002.1039212"},{"key":"ref35","first-page":"21205","article-title":"LIDL: Local intrinsic dimension estimation using approximate likelihood","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tempczyk","year":"2022"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00290"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i6.25949"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007379606734"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390177"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d17-1206"},{"key":"ref41","article-title":"The natural language decathlon: Multitask learning as question answering","author":"McCann","year":"2018"},{"key":"ref42","first-page":"5799","article-title":"Muppet: Massive multi-task representations with pre-finetuning","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Aghajanyan","year":"2021"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.171"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.244"},{"key":"ref45","article-title":"Entailment as few-shot learner","author":"Wang","year":"2021"},{"key":"ref46","article-title":"Training language models to follow instructions with human feedback","author":"Ouyang","year":"2022"},{"key":"ref47","first-page":"7163","article-title":"CrossFit: A few-shot learning challenge for cross-task generalization in NLP","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Ye","year":"2021"},{"key":"ref48","article-title":"Measuring massive multitask language understanding","author":"Hendrycks","year":"2020"},{"key":"ref49","article-title":"Multitask prompted training enables zero-shot task generalization","author":"Sanh","year":"2021"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.244"},{"key":"ref51","article-title":"Beyond the imitation game: Quantifying and extrapolating the capabilities of language models","author":"Srivastava","year":"2022"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.340"},{"key":"ref53","article-title":"Finetuned language models are zero-shot learners","author":"Wei","year":"2021"},{"key":"ref54","article-title":"Scaling instruction-finetuned language models","author":"Chung","year":"2022"},{"key":"ref55","article-title":"ChatGPT: Optimizing language models for dialogue","author":"Schulman","year":"2022"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref57","first-page":"10","article-title":"Generating sentences from a continuous space","volume-title":"Proc. 20th SIGNLL Conf. Comput. Natural Lang. Learn.","author":"Bowman","year":"2016"},{"key":"ref58","doi-asserted-by":"crossref","first-page":"7871","DOI":"10.18653\/v1\/2020.acl-main.703","article-title":"BART: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension","volume-title":"Proc. 58th Annu. Meeting Assoc. Comput. Linguistics","author":"Lewis","year":"2020"},{"key":"ref59","first-page":"1896","article-title":"UNIFIEDQA: Crossing format boundaries with a single QA system","volume-title":"Proc. Findings Assoc. Comput. Linguistics","author":"Khashabi","year":"2020"},{"key":"ref60","article-title":"Decoupled weight decay regularization","volume-title":"Proc. 7th Int. Conf. Learn. Representations","author":"Loshchilov","year":"2019"},{"key":"ref61","doi-asserted-by":"crossref","DOI":"10.21203\/rs.3.rs-1553541\/v1","article-title":"Delta tuning: A comprehensive study of parameter efficient methods for pre-trained language models","author":"Ding","year":"2022"},{"key":"ref62","article-title":"Fastfood-approximating kernel expansions in loglinear time","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Le","year":"2013"},{"key":"ref63","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Houlsby","year":"2019"},{"key":"ref64","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021"},{"key":"ref65","article-title":"Scaling laws for neural language models","author":"Kaplan","year":"2020"},{"key":"ref66","article-title":"Finetuned language models are zero-shot learners","author":"Wei","year":"2021"},{"key":"ref67","article-title":"Towards a unified view of parameter-efficient transfer learning","author":"He","year":"2021"},{"key":"ref68","first-page":"3348","article-title":"Different tunes played with equal skill: Exploring a unified optimization subspace for parameter-efficient tuning","volume-title":"Proc. Findings Assoc. Comput. Linguistics","author":"Yi","year":"2022"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6570655\/10304349\/10603438.pdf?arnumber=10603438","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,31]],"date-time":"2024-07-31T05:33:30Z","timestamp":1722404010000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10603438\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":68,"URL":"https:\/\/doi.org\/10.1109\/taslp.2024.3430545","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}