{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:08:18Z","timestamp":1777889298480,"version":"3.51.4"},"reference-count":24,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T00:00:00Z","timestamp":1750204800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T00:00:00Z","timestamp":1750204800000},"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":["Sci. China Inf. Sci."],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1007\/s11432-023-3911-2","type":"journal-article","created":{"date-parts":[[2025,6,21]],"date-time":"2025-06-21T06:26:04Z","timestamp":1750487164000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Improving cross-task generalization with step-by-step instructions"],"prefix":"10.1007","volume":"68","author":[{"given":"Yang","family":"Wu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanyan","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhongyang","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bing","family":"Qin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kai","family":"Xiong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,6,18]]},"reference":[{"key":"3911_CR1","first-page":"7163","volume-title":"Proceedings of the Conference on Empirical Methods in Natural Language Processing, Punta Cana","author":"Q Y Ye","year":"2021","unstructured":"Ye Q Y, Lin B Y C, Ren X. CrossFit: a few-shot learning challenge for cross-task generalization in NLP. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing, Punta Cana, 2021. 7163\u20137189"},{"key":"3911_CR2","first-page":"3470","volume-title":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics, Dublin","author":"S Mishra","year":"2022","unstructured":"Mishra S, Khashabi D, Baral C, et al. Cross-task generalization via natural language crowdsourcing instructions. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics, Dublin, 2022. 3470\u20133487"},{"key":"3911_CR3","doi-asserted-by":"publisher","first-page":"5085","DOI":"10.18653\/v1\/2022.emnlp-main.340","volume-title":"Proceedings of the Conference on Empirical Methods in Natural Language Processing, Abu Dhabi","author":"Y Z Wang","year":"2022","unstructured":"Wang Y Z, Mishra S, Alipoormolabashi P, et al. Super-naturalinstructions: generalization via declarative instructions on 1600+ tasks. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing, Abu Dhabi, 2022. 5085\u20135109"},{"key":"3911_CR4","volume-title":"Proceedings of the International Conference on Learning Representations","author":"V Sanh","year":"2022","unstructured":"Sanh V, Webson A, Raffel C, et al. Multitask prompted training enables zero-shot task generalization. In: Proceedings of the International Conference on Learning Representations, 2022"},{"key":"3911_CR5","volume-title":"Scaling instruction-finetuned language models","author":"W H Chung","year":"2022","unstructured":"Chung W H, Hou L, Longpre S, et al. Scaling instruction-finetuned language models. 2022. ArXiv:221011416"},{"key":"3911_CR6","volume-title":"Holistic evaluation of language models","author":"P Liang","year":"2022","unstructured":"Liang P, Bommasani R, Tsipras D, et al. Holistic evaluation of language models. 2022. ArXiv:221109110"},{"key":"3911_CR7","volume-title":"Proceedings of the International Conference on Learning Representations","author":"D Hendrycks","year":"2021","unstructured":"Hendrycks D, Burns C, Basart S, et al. Measuring massive multitask language understanding. In: Proceedings of the International Conference on Learning Representations, 2021"},{"key":"3911_CR8","volume-title":"Challenging big-bench tasks and whether chain-of-thought can solve them","author":"M Suzgun","year":"2022","unstructured":"Suzgun M, Scales N, Sch\u00e4rli N, et al. Challenging big-bench tasks and whether chain-of-thought can solve them. 2022. ArXiv:221009261"},{"key":"3911_CR9","first-page":"3008","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","author":"N Stiennon","year":"2022","unstructured":"Stiennon N, Ouyang L, Wu J, et al. Learning to summarize with human feedback. In: Proceedings of the Advances in Neural Information Processing Systems, 2022. 3008\u20133021"},{"key":"3911_CR10","first-page":"1877","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","author":"T Brown","year":"2020","unstructured":"Brown T, Mann B, Ryder N, et al. Language models are few-shot learners. In: Proceedings of the Advances in Neural Information Processing Systems, 2020. 1877\u20131901"},{"key":"3911_CR11","volume-title":"Bloom: a 176b-parameter open-access multilingual language model","author":"T L Scao","year":"2022","unstructured":"Scao T L, Fan A, Akiki C, et al. Bloom: a 176b-parameter open-access multilingual language model. 2022. ArXiv:221105100"},{"key":"3911_CR12","volume-title":"Proceedings of the International Conference on Learning Representations","author":"A Zeng","year":"2023","unstructured":"Zeng A, Liu X, Du Z X, et al. GLM-130b: an open bilingual pre-trained model. In: Proceedings of the International Conference on Learning Representations, 2023"},{"key":"3911_CR13","volume-title":"Proceedings of the International Conference on Learning Representations","author":"J Wei","year":"2022","unstructured":"Wei J, Bosma M, Zhao V, et al. Finetuned language models are zero-shot learners. In: Proceedings of the International Conference on Learning Representations, 2022"},{"key":"3911_CR14","first-page":"589","volume-title":"Proceedings of the Findings of the Association for Computational Linguistics, Dublin","author":"S Mishra","year":"2022","unstructured":"Mishra S, Khashabi D, Baral C, et al. Reframing instructional prompts to GPTk\u2019s language. In: Proceedings of the Findings of the Association for Computational Linguistics, Dublin, 2022. 589\u2013612"},{"key":"3911_CR15","first-page":"24824","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","author":"J Wei","year":"2022","unstructured":"Wei J, Wang X Z, Schuurmans D, et al. Chain of thought prompting elicits reasoning in large language models. In: Proceedings of the Advances in Neural Information Processing Systems, 2022. 24824\u201324837"},{"key":"3911_CR16","first-page":"22199","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","author":"T Kojima","year":"2022","unstructured":"Kojima T, Gu S X S, Reid M, et al. Large language models are zero-shot reasoners. In: Proceedings of the Advances in Neural Information Processing Systems, 2022. 22199\u201322213"},{"key":"3911_CR17","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Z S Zhang","year":"2023","unstructured":"Zhang Z S, Zhang A, Li M, et al. Automatic chain of thought prompting in large language models. In: Proceedings of the International Conference on Learning Representations, 2023"},{"key":"3911_CR18","volume-title":"Proceedings of the International Conference on Learning Representations","author":"D Zhou","year":"2023","unstructured":"Zhou D, Sch\u00e4rli N, Hou L, et al. Least-to-most prompting enables complex reasoning in large language models. In: Proceedings of the International Conference on Learning Representations, 2023"},{"key":"3911_CR19","volume-title":"Proceedings of the International Conference on Learning Representations","author":"T Khot","year":"2023","unstructured":"Khot T, Trivedi H, Finlayson M, et al. Decomposed prompting: a modular approach for solving complex tasks. In: Proceedings of the International Conference on Learning Representations, 2023"},{"key":"3911_CR20","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2305016120","volume-title":"ChatGPT outperforms crowd-workers for text-annotation tasks","author":"F Gilardi","year":"2023","unstructured":"Gilardi F, Alizadeh M, Kubli M. ChatGPT outperforms crowd-workers for text-annotation tasks. 2023. ArXiv:230315056"},{"key":"3911_CR21","volume-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","author":"C Raffel","year":"2020","unstructured":"Raffel C, Shazeer N, Roberts A, et al. Exploring the limits of transfer learning with a unified text-to-text transformer. 2020. ArXiv:1910.10683"},{"key":"3911_CR22","first-page":"74","volume-title":"Proceedings of the Text Summarization Branches Out, Barcelona","author":"C Y Lin","year":"2004","unstructured":"Lin C Y. ROUGE: a package for automatic evaluation of summaries. In: Proceedings of the Text Summarization Branches Out, Barcelona, 2004. 74\u201381"},{"key":"3911_CR23","first-page":"27730","volume-title":"Proceedings of the Advances in Neural Information Processing Systems, Barcelona","author":"L Ouyang","year":"2022","unstructured":"Ouyang L, Wu J, Jiang X, et al. Training language models to follow instructions with human feedback. In: Proceedings of the Advances in Neural Information Processing Systems, Barcelona, 2022. 27730\u201327744"},{"key":"3911_CR24","doi-asserted-by":"publisher","first-page":"378","DOI":"10.1037\/h0031619","volume":"76","author":"J L Fleiss","year":"1971","unstructured":"Fleiss J L. Measuring nominal scale agreement among many raters. Psycholog Bull, 1971, 76: 378\u2013382","journal-title":"Psycholog Bull"}],"container-title":["Science China Information Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11432-023-3911-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11432-023-3911-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11432-023-3911-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,21]],"date-time":"2025-06-21T06:26:10Z","timestamp":1750487170000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11432-023-3911-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,18]]},"references-count":24,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2025,7]]}},"alternative-id":["3911"],"URL":"https:\/\/doi.org\/10.1007\/s11432-023-3911-2","relation":{},"ISSN":["1674-733X","1869-1919"],"issn-type":[{"value":"1674-733X","type":"print"},{"value":"1869-1919","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,18]]},"assertion":[{"value":"5 June 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 October 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 December 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 June 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"172102"}}