{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T23:13:38Z","timestamp":1789082018671,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031891021","type":"print"},{"value":"9783031891038","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-89103-8_4","type":"book-chapter","created":{"date-parts":[[2025,4,24]],"date-time":"2025-04-24T07:29:04Z","timestamp":1745479744000},"page":"48-64","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Feature Generation Using LLMs: An Evolutionary Algorithm Approach"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-2233-3155","authenticated-orcid":false,"given":"Aria","family":"Nourbakhsh","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7507-5328","authenticated-orcid":false,"given":"Beno\u00eet","family":"Alcaraz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0308-7637","authenticated-orcid":false,"given":"Christoph","family":"Schommer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,4,25]]},"reference":[{"key":"4_CR1","doi-asserted-by":"publisher","unstructured":"Aeberhard, S., Forina, M.: Wine. UCI Machine Learning Repository (1992). https:\/\/doi.org\/10.24432\/C5PC7J","DOI":"10.24432\/C5PC7J"},{"key":"4_CR2","unstructured":"Ahn, J., Verma, R., Lou, R., Liu, D., Zhang, R., Yin, W.: Large language models for mathematical reasoning: Progresses and challenges. arXiv preprint arXiv:2402.00157 (2024)"},{"key":"4_CR3","unstructured":"Bellman, R.: Dynamic programming. Princeton University Press, Princeton (1957)"},{"issue":"8","key":"4_CR4","doi-asserted-by":"publisher","first-page":"1798","DOI":"10.1109\/TPAMI.2013.50","volume":"35","author":"Y Bengio","year":"2013","unstructured":"Bengio, Y., Courville, A., Vincent, P.: Representation learning: a review and new perspectives. IEEE Trans. Pattern Anal. Mach. Intell. 35(8), 1798\u20131828 (2013). https:\/\/doi.org\/10.1109\/TPAMI.2013.50","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"4_CR5","doi-asserted-by":"publisher","unstructured":"Bohanec, M.: Car Evaluation. UCI Machine Learning Repository (1997). https:\/\/doi.org\/10.24432\/C5JP48","DOI":"10.24432\/C5JP48"},{"issue":"3","key":"4_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3641289","volume":"15","author":"Y Chang","year":"2024","unstructured":"Chang, Y., et al.: A survey on evaluation of large language models. ACM Trans. Intell. Syst. Technol. 15(3), 1\u201345 (2024)","journal-title":"ACM Trans. Intell. Syst. Technol."},{"key":"4_CR7","unstructured":"Coates, A., Ng, A., Lee, H.: An analysis of single-layer networks in unsupervised feature learning. In: Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, pp. 215\u2013223. JMLR Workshop and Conference Proceedings (2011)"},{"issue":"1","key":"4_CR8","doi-asserted-by":"publisher","first-page":"114","DOI":"10.3390\/digital4010005","volume":"4","author":"C Coello","year":"2024","unstructured":"Coello, C., Alimam, M.N., Kouatly, R.: Effectiveness of chatgpt in coding: a comparative analysis of popular large language models. Digital 4(1), 114\u2013125 (2024)","journal-title":"Digital"},{"issue":"1\u20134","key":"4_CR9","doi-asserted-by":"publisher","first-page":"131","DOI":"10.3233\/IDA-1997-1302","volume":"1","author":"M Dash","year":"1997","unstructured":"Dash, M., Liu, H.: Feature selection for classification. Intell. Data Anal. 1(1\u20134), 131\u2013156 (1997)","journal-title":"Intell. Data Anal."},{"key":"4_CR10","doi-asserted-by":"publisher","first-page":"176","DOI":"10.1016\/j.ins.2011.11.039","volume":"189","author":"O Dor","year":"2012","unstructured":"Dor, O., Reich, Y.: Strengthening learning algorithms by feature discovery. Inf. Sci. 189, 176\u2013190 (2012)","journal-title":"Inf. Sci."},{"key":"4_CR11","unstructured":"Dubey, A., et al.: The llama 3 herd of models (2024). https:\/\/arxiv.org\/abs\/2407.21783"},{"key":"4_CR12","unstructured":"Han, S., Yoon, J., Arik, S.O., Pfister, T.: Large language models can automatically engineer features for few-shot tabular learning. In: Salakhutdinov, R., Kolter, Z., Heller, K., Weller, A., Oliver, N., Scarlett, J., Berkenkamp, F. (eds.) Proceedings of the 41st International Conference on Machine Learning. Proceedings of Machine Learning Research, vol.\u00a0235, pp. 17454\u201317479. PMLR (2024). https:\/\/proceedings.mlr.press\/v235\/han24f.html"},{"key":"4_CR13","doi-asserted-by":"crossref","unstructured":"Heaton, J.: An empirical analysis of feature engineering for predictive modeling. In: SoutheastCon 2016, pp.\u00a01\u20136. IEEE (2016)","DOI":"10.1109\/SECON.2016.7506650"},{"key":"4_CR14","unstructured":"Jeong, D.P., Lipton, Z.C., Ravikumar, P.: Llm-select: Feature selection with large language models. arXiv preprint arXiv:2407.02694 (2024)"},{"key":"4_CR15","doi-asserted-by":"crossref","unstructured":"Karabacak, M., Margetis, K.: Embracing large language models for medical applications: opportunities and challenges. Cureus 15(5) (2023)","DOI":"10.7759\/cureus.39305"},{"key":"4_CR16","doi-asserted-by":"crossref","unstructured":"Katz, G., Shin, E.C.R., Song, D.: Explorekit: automatic feature generation and selection. In: 2016 IEEE 16th International Conference on Data Mining (ICDM). pp. 979\u2013984. IEEE (2016)","DOI":"10.1109\/ICDM.2016.0123"},{"key":"4_CR17","doi-asserted-by":"crossref","unstructured":"Khurana, U., Samulowitz, H., Turaga, D.: Feature engineering for predictive modeling using reinforcement learning. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol.\u00a032 (2018)","DOI":"10.1609\/aaai.v32i1.11678"},{"key":"4_CR18","doi-asserted-by":"crossref","unstructured":"Khurana, U., Turaga, D., Samulowitz, H., Parthasrathy, S.: Cognito: Automated feature engineering for supervised learning. In: 2016 IEEE 16th International Conference on Data Mining Workshops (ICDMW). pp. 1304\u20131307. IEEE (2016)","DOI":"10.1109\/ICDMW.2016.0190"},{"key":"4_CR19","unstructured":"Li, D., Tan, Z., Liu, H.: Exploring large language models for feature selection: A data-centric perspective. arXiv preprint arXiv:2408.12025 (2024)"},{"key":"4_CR20","doi-asserted-by":"crossref","unstructured":"Li, Y., Wang, S., Ding, H., Chen, H.: Large language models in finance: a survey. In: Proceedings of the fourth ACM International Conference on AI in finance, pp. 374\u2013382 (2023)","DOI":"10.1145\/3604237.3626869"},{"key":"4_CR21","unstructured":"Liu, J., Xia, C.S., Wang, Y., Zhang, L.: Is your code generated by chatgpt really correct? rigorous evaluation of large language models for code generation. Adv. Neural Inform. Proce. Syst. 36 (2024)"},{"key":"4_CR22","doi-asserted-by":"publisher","unstructured":"Liu, Z.: Amazon commerce reviews. UCI Mach. Learn. Repository (2011). https:\/\/doi.org\/10.24432\/C55C88","DOI":"10.24432\/C55C88"},{"key":"4_CR23","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1023\/A:1014046307775","volume":"49","author":"S Markovitch","year":"2002","unstructured":"Markovitch, S., Rosenstein, D.: Feature generation using general constructor functions. Mach. Learn. 49, 59\u201398 (2002)","journal-title":"Mach. Learn."},{"key":"4_CR24","unstructured":"Meyerson, E., et al.: Language model crossover: Variation through few-shot prompting. arXiv preprint arXiv:2302.12170 (2023)"},{"issue":"67\u201372","key":"4_CR25","first-page":"2","volume":"5","author":"H Motoda","year":"2002","unstructured":"Motoda, H., Liu, H.: Feature selection, extraction and construction. Commun. IICM (Inst. Inform. Comput. Mach. Taiwan) 5(67\u201372), 2 (2002)","journal-title":"Commun. IICM (Inst. Inform. Comput. Mach. Taiwan)"},{"key":"4_CR26","doi-asserted-by":"publisher","unstructured":"Nash, W., Sellers, T., Talbot, S., Cawthorn, A., Ford, W.: Abalone. UCI Mach. Learn. Repository (1995). https:\/\/doi.org\/10.24432\/C55C7W","DOI":"10.24432\/C55C7W"},{"issue":"2","key":"4_CR27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3597307","volume":"15","author":"R Navigli","year":"2023","unstructured":"Navigli, R., Conia, S., Ross, B.: Biases in large language models: origins, inventory, and discussion. ACM J. Data Inform. Qual. 15(2), 1\u201321 (2023)","journal-title":"ACM J. Data Inform. Qual."},{"key":"4_CR28","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa, F., et al.: Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825\u20132830 (2011)","journal-title":"J. Mach. Learn. Res."},{"key":"4_CR29","doi-asserted-by":"crossref","unstructured":"Realinho, V., Machado, J., Baptista, L., Martins, M.V.: Predict students\u2019 dropout and academic success. UCI Mach. Learn. Repository (2021). DOI: https:\/\/doi.org\/10.24432\/C5MC89","DOI":"10.3390\/data7110146"},{"issue":"7995","key":"4_CR30","doi-asserted-by":"publisher","first-page":"468","DOI":"10.1038\/s41586-023-06924-6","volume":"625","author":"B Romera-Paredes","year":"2024","unstructured":"Romera-Paredes, B., et al.: Mathematical discoveries from program search with large language models. Nature 625(7995), 468\u2013475 (2024)","journal-title":"Nature"},{"key":"4_CR31","doi-asserted-by":"publisher","unstructured":"Shafti, L.S., P\u00e9rez, E.P.: Constructive induction and genetic algorithms for learning concepts with complex interaction. In: Proceedings of the 7th Annual Conference on Genetic and Evolutionary Computation. pp. 1811-1818. GECCO \u201905, Association for Computing Machinery, New York, NY, USA (2005). https:\/\/doi.org\/10.1145\/1068009.1068317","DOI":"10.1145\/1068009.1068317"},{"key":"4_CR32","doi-asserted-by":"crossref","unstructured":"Sutton, R.S., Matheus, C.J.: Learning polynomial functions by feature construction. In: Machine Learning Proceedings 1991, pp. 208\u2013212. Elsevier (1991)","DOI":"10.1016\/B978-1-55860-200-7.50045-3"},{"key":"4_CR33","unstructured":"Tang, J., Alelyani, S., Liu, H.: Feature selection for classification: a review. Data Classif.: Algorithms Appl. 37 (2014)"},{"key":"4_CR34","doi-asserted-by":"publisher","unstructured":"pandas development team, T.: pandas-dev\/pandas: Pandas (2020). https:\/\/doi.org\/10.5281\/zenodo.3509134","DOI":"10.5281\/zenodo.3509134"},{"key":"4_CR35","unstructured":"Teboul, A.: Diabetes health indicators dataset (2022). https:\/\/www.kaggle.com\/datasets\/alexteboul\/diabetes-health-indicators-dataset. Accessed insert-date-here"},{"key":"4_CR36","unstructured":"Sigillito, V., Wing, S., Hutton, L., Baker, K.: Ionosphere. UCI Mach. Learn. Repository (1989). https:\/\/doi.org\/10.24432\/C5W01B"},{"key":"4_CR37","doi-asserted-by":"crossref","unstructured":"Wang, Z.: Causalbench: A comprehensive benchmark for evaluating causal reasoning capabilities of large language models. In: Proceedings of the 10th SIGHAN Workshop on Chinese Language Processing (SIGHAN-10), pp. 143\u2013151 (2024)","DOI":"10.18653\/v1\/2024.sighan-1.17"},{"key":"4_CR38","doi-asserted-by":"publisher","unstructured":"Wnek, J.: MONK\u2019s problems. UCI Mach. Learn. Repository (1992). https:\/\/doi.org\/10.24432\/C5R30R","DOI":"10.24432\/C5R30R"},{"key":"4_CR39","unstructured":"Wu, X., Wu, S.h., Wu, J., Feng, L., Tan, K.C.: Evolutionary computation in the era of large language model: Surv. Roadmap. arXiv preprint arXiv:2401.10034 (2024)"},{"key":"4_CR40","unstructured":"Zhang, X., Zhang, J., Rekabdar, B., Zhou, Y., Wang, P., Liu, K.: Dynamic and adaptive feature generation with llm. arXiv preprint arXiv:2406.03505 (2024)"}],"container-title":["Communications in Computer and Information Science","Advances in Explainability, Agents, and Large Language Models"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-89103-8_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,24]],"date-time":"2025-04-24T07:29:20Z","timestamp":1745479760000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-89103-8_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031891021","9783031891038"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-89103-8_4","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"25 April 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"None of the author of the paper is having a conflict of interest.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"CALM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Workshop on Causality, Agents and Large Models","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kyoto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","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":"18 November 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 November 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"calm2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.ciad-lab.fr\/prima-causal-ai-workshop\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}