{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,24]],"date-time":"2025-12-24T12:34:43Z","timestamp":1766579683408,"version":"3.40.3"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031702419"},{"type":"electronic","value":"9783031702426"}],"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\/978-3-031-70242-6_26","type":"book-chapter","created":{"date-parts":[[2024,9,19]],"date-time":"2024-09-19T10:03:06Z","timestamp":1726740186000},"page":"269-279","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Enhancing Small Language Models via\u00a0ChatGPT and\u00a0Dataset Augmentation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-8978-6577","authenticated-orcid":false,"given":"Tom","family":"Pieper","sequence":"first","affiliation":[]},{"given":"Mohamad","family":"Ballout","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1976-8186","authenticated-orcid":false,"given":"Ulf","family":"Krumnack","sequence":"additional","affiliation":[]},{"given":"Gunther","family":"Heidemann","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1626-0598","authenticated-orcid":false,"given":"Kai-Uwe","family":"K\u00fchnberger","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,9,20]]},"reference":[{"key":"26_CR1","unstructured":"Ballout, M., Krumnack, U., Heidemann, G., Kuehnberger, K.U.: Show me how it\u2019s done: the role of explanations in fine-tuning language models (2024)"},{"key":"26_CR2","unstructured":"Brown, T.B., et al.: Language models are few-shot learners, May 2020. http:\/\/arxiv.org\/abs\/2005.14165"},{"key":"26_CR3","doi-asserted-by":"publisher","unstructured":"Bucil, C., Caruana, R., Niculescu-Mizil, A.: Model compression. In: Proceedings of the 12th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2006, pp. 535\u2013541. Association for Computing Machinery, New York (2006). https:\/\/doi.org\/10.1145\/1150402.1150464","DOI":"10.1145\/1150402.1150464"},{"key":"26_CR4","unstructured":"Camburu, O.M., Rockt\u00e4schel, T., Lukasiewicz, T., Blunsom, P.: e-SNLI: natural language inference with natural language explanations (2018)"},{"key":"26_CR5","doi-asserted-by":"crossref","unstructured":"Chakrabarty, T., Saakyan, A., Ghosh, D., Muresan, S.: FLUTE: figurative language understanding through textual explanations (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.481"},{"key":"26_CR6","doi-asserted-by":"crossref","unstructured":"DeYoung, J., et al.: ERASER: a benchmark to evaluate rationalized NLP models (2020)","DOI":"10.18653\/v1\/2020.acl-main.408"},{"key":"26_CR7","unstructured":"Github Repository. https:\/\/github.com\/tomlpieper\/ba. Accessed 24 May 2024"},{"key":"26_CR8","doi-asserted-by":"publisher","unstructured":"Hase, P., Bansal, M.: When can models learn from explanations? A formal framework for understanding the roles of explanation data. In: Andreas, J., Narasimhan, K., Nematzadeh, A. (eds.) Proceedings of the First Workshop on Learning with Natural Language Supervision, Dublin, Ireland, pp. 29\u201339. Association for Computational Linguistics, May 2022. https:\/\/doi.org\/10.18653\/v1\/2022.lnls-1.4. https:\/\/aclanthology.org\/2022.lnls-1.4","DOI":"10.18653\/v1\/2022.lnls-1.4"},{"key":"26_CR9","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network (2015)"},{"key":"26_CR10","doi-asserted-by":"crossref","unstructured":"Ho, N., Schmid, L., Yun, S.Y.: Large language models are reasoning teachers (2023)","DOI":"10.18653\/v1\/2023.acl-long.830"},{"key":"26_CR11","doi-asserted-by":"crossref","unstructured":"Hsieh, C.Y., et al.: Distilling step-by-step! Outperforming larger language models with less training data and smaller model sizes (2023)","DOI":"10.18653\/v1\/2023.findings-acl.507"},{"key":"26_CR12","unstructured":"Li, S., et al.: Explanations from large language models make small reasoners better (2022)"},{"key":"26_CR13","doi-asserted-by":"publisher","unstructured":"Liu, A., Swayamdipta, S., Smith, N.A., Choi, Y.: WANLI: worker and AI collaboration for natural language inference dataset creation. In: Goldberg, Y., Kozareva, Z., Zhang, Y. (eds.) Findings of the Association for Computational Linguistics: EMNLP 2022, Abu Dhabi, United Arab Emirates, pp. 6826\u20136847. Association for Computational Linguistics, December 2022. https:\/\/doi.org\/10.18653\/v1\/2022.findings-emnlp.508. https:\/\/aclanthology.org\/2022.findings-emnlp.508","DOI":"10.18653\/v1\/2022.findings-emnlp.508"},{"key":"26_CR14","doi-asserted-by":"crossref","unstructured":"MacCartney, B., Manning, C.D.: Modeling semantic containment and exclusion in natural language inference. In: Scott, D., Uszkoreit, H. (eds.) Proceedings of the 22nd International Conference on Computational Linguistics (Coling 2008), Manchester, UK, pp. 521\u2013528. Coling 2008 Organizing Committee, August 2008. https:\/\/aclanthology.org\/C08-1066","DOI":"10.3115\/1599081.1599147"},{"key":"26_CR15","unstructured":"Meng, Y., Huang, J., Zhang, Y., Han, J.: Generating training data with language models: towards zero-shot language understanding (2022)"},{"key":"26_CR16","unstructured":"Narang, S., Raffel, C., Lee, K., Roberts, A., Fiedel, N., Malkan, K.: Wt5?! Training text-to-text models to explain their predictions (2020)"},{"key":"26_CR17","doi-asserted-by":"crossref","unstructured":"Nie, Y., Williams, A., Dinan, E., Bansal, M., Weston, J., Kiela, D.: Adversarial NLI: a new benchmark for natural language understanding (2020)","DOI":"10.18653\/v1\/2020.acl-main.441"},{"key":"26_CR18","doi-asserted-by":"publisher","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: BLEU: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting on Association for Computational Linguistics, pp. 311\u2013318, ACL 2002. Association for Computational Linguistics, USA (2002). https:\/\/doi.org\/10.3115\/1073083.1073135. https:\/\/doi.org\/10.3115\/1073083.1073135","DOI":"10.3115\/1073083.1073135"},{"key":"26_CR19","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer (2023)"},{"key":"26_CR20","doi-asserted-by":"crossref","unstructured":"Rajani, N.F., McCann, B., Xiong, C., Socher, R.: Explain yourself! Leveraging language models for commonsense reasoning (2019)","DOI":"10.18653\/v1\/P19-1487"},{"key":"26_CR21","doi-asserted-by":"publisher","unstructured":"Barattieri\u00a0di San\u00a0Pietro, C., Frau, F., Mangiaterra, V., Bambini, V.: The pragmatic profile of chatGPT: assessing the communicative skills of a conversational agent. Sistemi Intelligenti XXXV, 379\u2013400 (2023). https:\/\/doi.org\/10.1422\/108136","DOI":"10.1422\/108136"},{"key":"26_CR22","unstructured":"Talmor, A., Herzig, J., Lourie, N., Berant, J.: CommonsenseQA: a question answering challenge targeting commonsense knowledge (2019)"},{"key":"26_CR23","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1007\/978-1-4842-7092-9_7","volume-title":"Generating a New Reality","author":"M Lanham","year":"2021","unstructured":"Lanham, M.: Attention is all we need! In: Generating a New Reality, pp. 195\u2013222. Apress, Berkeley (2021). https:\/\/doi.org\/10.1007\/978-1-4842-7092-9_7"},{"issue":"6","key":"26_CR24","doi-asserted-by":"publisher","first-page":"3048","DOI":"10.1109\/TPAMI.2021.3055564","volume":"44","author":"L Wang","year":"2022","unstructured":"Wang, L., Yoon, K.J.: Knowledge distillation and student-teacher learning for visual intelligence: a review and new outlooks. IEEE Trans. Pattern Anal. Mach. Intell. 44(6), 3048\u20133068 (2022). https:\/\/doi.org\/10.1109\/TPAMI.2021.3055564","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"26_CR25","doi-asserted-by":"crossref","unstructured":"Wang, R., Zhou, W., Sachan, M.: Let\u2019s synthesize step by step: Iterative dataset synthesis with large language models by extrapolating errors from small models (2023)","DOI":"10.18653\/v1\/2023.findings-emnlp.791"},{"key":"26_CR26","unstructured":"Wei, J., et al.: Finetuned language models are zero-shot learners (2022)"},{"key":"26_CR27","unstructured":"Wei, J., et al.: Chain-of-thought prompting elicits reasoning in large language models (2023)"},{"key":"26_CR28","unstructured":"Wolf, T., et al.: HuggingFace\u2019s transformers: state-of-the-art natural language processing (2020)"},{"key":"26_CR29","doi-asserted-by":"crossref","unstructured":"Ye, J., et al.: ZEROGEN: efficient zero-shot learning via dataset generation (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.801"}],"container-title":["Lecture Notes in Computer Science","Natural Language Processing and Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-70242-6_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,24]],"date-time":"2025-02-24T12:14:53Z","timestamp":1740399293000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-70242-6_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031702419","9783031702426"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-70242-6_26","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":"20 September 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"NLDB","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Applications of Natural Language to Information Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Turin","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","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":"25 June 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 June 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"nldb2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/nldb2024.di.unito.it\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}