{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T19:46:06Z","timestamp":1778355966955,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":36,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,21]],"date-time":"2024-10-21T00:00:00Z","timestamp":1729468800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,21]]},"DOI":"10.1145\/3627673.3679153","type":"proceedings-article","created":{"date-parts":[[2024,10,20]],"date-time":"2024-10-20T19:34:11Z","timestamp":1729452851000},"page":"5420-5424","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["ELF-Gym: Evaluating Large Language Models Generated Features for Tabular Prediction"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-0104-238X","authenticated-orcid":false,"given":"Yanlin","family":"Zhang","sequence":"first","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-5941-6412","authenticated-orcid":false,"given":"Ning","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-0986-457X","authenticated-orcid":false,"given":"Quan","family":"Gan","sequence":"additional","affiliation":[{"name":"Amazon Shanghai AI Lab, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0127-2425","authenticated-orcid":false,"given":"Weinan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2768-4540","authenticated-orcid":false,"given":"David","family":"Wipf","sequence":"additional","affiliation":[{"name":"Amazon Shanghai AI Lab, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-8156-1179","authenticated-orcid":false,"given":"Minjie","family":"Wang","sequence":"additional","affiliation":[{"name":"Amazon Shanghai AI Lab, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,21]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al.","author":"Achiam Josh","year":"2023","unstructured":"Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al. 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)."},{"key":"e_1_3_2_1_2_1","unstructured":"AI@Meta. 2024. Llama 3 Model Card. (2024). https:\/\/github.com\/meta-llama\/llama3\/blob\/main\/MODEL_CARD.md"},{"key":"e_1_3_2_1_3_1","unstructured":"alokgupta Anna Montoya LizSellier Meghan O'Connell and Wendy Kan. 2015. Airbnb New User Bookings. https:\/\/kaggle.com\/competitions\/airbnb-recruiting-new-user-bookings"},{"key":"e_1_3_2_1_4_1","volume-title":"The claude 3 model family: Opus, sonnet, haiku. Claude-3 Model Card","author":"Anthropic AI","year":"2024","unstructured":"AI Anthropic. 2024. The claude 3 model family: Opus, sonnet, haiku. Claude-3 Model Card (2024)."},{"key":"e_1_3_2_1_5_1","unstructured":"Jacob Austin Augustus Odena Maxwell Nye Maarten Bosma Henryk Michalewski David Dohan Ellen Jiang Carrie Cai Michael Terry Quoc Le et al. 2021. Program synthesis with large language models. arXiv preprint arXiv:2108.07732 (2021)."},{"key":"e_1_3_2_1_6_1","volume-title":"Falcon-7b-instruct, and OpenAI Chat-GPT Models. arXiv preprint arXiv:2310.10449","author":"Basyal Lochan","year":"2023","unstructured":"Lochan Basyal and Mihir Sanghvi. 2023. Text Summarization Using Large Language Models: A Comparative Study of MPT-7b-instruct, Falcon-7b-instruct, and OpenAI Chat-GPT Models. arXiv preprint arXiv:2310.10449 (2023)."},{"key":"e_1_3_2_1_7_1","volume-title":"Jared Kaplan, Harri Edwards, Yuri Burda, Nicholas Joseph, Greg Brockman, et al.","author":"Chen Mark","year":"2021","unstructured":"Mark Chen, Jerry Tworek, Heewoo Jun, Qiming Yuan, Henrique Ponde de Oliveira Pinto, Jared Kaplan, Harri Edwards, Yuri Burda, Nicholas Joseph, Greg Brockman, et al. 2021. Evaluating large language models trained on code. arXiv preprint arXiv:2107.03374 (2021)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"e_1_3_2_1_9_1","unstructured":"DannyBickson Freedom Guy Rapaport HanZhu Ibrahim RossWang Wendy Kan Yangyang and Yao Lu. 2016. TalkingData Mobile User Demographics. https:\/\/kaggle.com\/competitions\/talkingdata-mobile-user-demographics"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3596490"},{"key":"e_1_3_2_1_11_1","volume-title":"Facebook Recruiting IV: Human or Robot? https:\/\/kaggle.com\/competitions\/facebook-recruiting-iv-human-or-bot","author":"Dullaghan Jim","year":"2015","unstructured":"Jim Dullaghan, John P. Costella, John_W, Meghan O'Connell, Rafael, Ruchi, Ruchi Varshney, Sergey, Sofus Macskassy, and Wendy Kan. 2015. Facebook Recruiting IV: Human or Robot? https:\/\/kaggle.com\/competitions\/facebook-recruiting-iv-human-or-bot"},{"key":"e_1_3_2_1_12_1","volume-title":"AutoGluon-Tabular: Robust and Accurate AutoML for Structured Data. arXiv preprint arXiv:2003.06505","author":"Erickson Nick","year":"2020","unstructured":"Nick Erickson, Jonas Mueller, Alexander Shirkov, Hang Zhang, Pedro Larroy, Mu Li, and Alexander Smola. 2020. AutoGluon-Tabular: Robust and Accurate AutoML for Structured Data. arXiv preprint arXiv:2003.06505 (2020)."},{"key":"e_1_3_2_1_13_1","volume-title":"Junyi Jessy Li, and Greg Durrett","author":"Goyal Tanya","year":"2022","unstructured":"Tanya Goyal, Junyi Jessy Li, and Greg Durrett. 2022. News summarization and evaluation in the era of gpt-3. arXiv preprint arXiv:2209.12356 (2022)."},{"key":"e_1_3_2_1_14_1","volume-title":"DS-Agent: Automated Data Science by Empowering Large Language Models with Case-Based Reasoning. arXiv preprint arXiv:2402.17453","author":"Guo Siyuan","year":"2024","unstructured":"Siyuan Guo, Cheng Deng, Ying Wen, Hechang Chen, Yi Chang, and Jun Wang. 2024. DS-Agent: Automated Data Science by Empowering Large Language Models with Case-Based Reasoning. arXiv preprint arXiv:2402.17453 (2024)."},{"key":"e_1_3_2_1_15_1","volume-title":"night_bat, and Wendy Kan","author":"Guz Ivan","year":"2015","unstructured":"Ivan Guz, night_bat, and Wendy Kan. 2015. Avito Context Ad Clicks. https:\/\/kaggle.com\/competitions\/avito-context-ad-clicks"},{"key":"e_1_3_2_1_16_1","volume-title":"Large Language Models Can Automatically Engineer Features for Few-Shot Tabular Learning. arXiv preprint arXiv:2404.09491","author":"Han Sungwon","year":"2024","unstructured":"Sungwon Han, Jinsung Yoon, Sercan O Arik, and Tomas Pfister. 2024. Large Language Models Can Automatically Engineer Features for Few-Shot Tabular Learning. arXiv preprint arXiv:2404.09491 (2024)."},{"key":"e_1_3_2_1_17_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Hollmann Noah","year":"2024","unstructured":"Noah Hollmann, Samuel M\u00fcller, and Frank Hutter. 2024. Large language models for automated data science: Introducing caafe for context-aware automated feature engineering. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-43823-4_10"},{"key":"e_1_3_2_1_19_1","volume-title":"John Lei, Lynn@Vesta, Marcus2010, and Prof. Hussein Abbass.","author":"Howard Addison","year":"2019","unstructured":"Addison Howard, Bernadette Bouchon-Meunier, IEEE CIS, inversion, John Lei, Lynn@Vesta, Marcus2010, and Prof. Hussein Abbass. 2019. IEEE-CIS Fraud Detection. https:\/\/kaggle.com\/competitions\/ieee-fraud-detection"},{"key":"e_1_3_2_1_20_1","unstructured":"sharathrao Will Cukierski jeremy stanley Meg Risdal. 2017. Instacart Market Basket Analysis. https:\/\/kaggle.com\/competitions\/instacart-market-basket-analysis"},{"key":"e_1_3_2_1_21_1","volume-title":"Diego de las Casas, Emma Bou Hanna, Florian Bressand, et al.","author":"Jiang Albert Q","year":"2024","unstructured":"Albert Q Jiang, Alexandre Sablayrolles, Antoine Roux, Arthur Mensch, Blanche Savary, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Emma Bou Hanna, Florian Bressand, et al. 2024. Mixtral of experts. arXiv preprint arXiv:2401.04088 (2024)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/2959100.2959134"},{"key":"e_1_3_2_1_23_1","unstructured":"Kaggle. [n. d.]. Kaggle. https:\/\/www.kaggle.com"},{"key":"e_1_3_2_1_24_1","unstructured":"Wendy Kan. 2015. West Nile Virus Prediction. https:\/\/kaggle.com\/competitions\/predict-west-nile-virus"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/DSAA.2015.7344858"},{"key":"e_1_3_2_1_26_1","volume-title":"Lightgbm: A highly efficient gradient boosting decision tree. Advances in neural information processing systems","author":"Ke Guolin","year":"2017","unstructured":"Guolin Ke, Qi Meng, Thomas Finley, Taifeng Wang, Wei Chen, Weidong Ma, Qiwei Ye, and Tie-Yan Liu. 2017. Lightgbm: A highly efficient gradient boosting decision tree. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_27_1","volume-title":"Bounding the capabilities of large language models in open text generation with prompt constraints. arXiv preprint arXiv:2302.09185","author":"Lu Albert","year":"2023","unstructured":"Albert Lu, Hongxin Zhang, Yanzhe Zhang, Xuezhi Wang, and Diyi Yang. 2023. Bounding the capabilities of large language models in open text generation with prompt constraints. arXiv preprint arXiv:2302.09185 (2023)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3605943"},{"key":"e_1_3_2_1_29_1","unstructured":"mjkistler Ran Locar Ronny Lempel RoySassonOB Rwagner and Will Cukierski. 2016. Outbrain Click Prediction. https:\/\/kaggle.com\/competitions\/outbrain-click-prediction"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","unstructured":"The pandas development team. 2020. pandas-dev\/pandas: Pandas. https:\/\/doi.org\/10.5281\/zenodo.3509134","DOI":"10.5281\/zenodo.3509134"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2010.127"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE48307.2020.00146"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3490099.3511105"},{"key":"e_1_3_2_1_34_1","volume-title":"Planning with large language models for code generation. arXiv preprint arXiv:2303.05510","author":"Zhang Shun","year":"2023","unstructured":"Shun Zhang, Zhenfang Chen, Yikang Shen, Mingyu Ding, Joshua B Tenenbaum, and Chuang Gan. 2023. Planning with large language models for code generation. arXiv preprint arXiv:2303.05510 (2023)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00632"},{"key":"e_1_3_2_1_36_1","volume-title":"Openfe: Automated feature generation beyond expert-level performance.","author":"Zhang Tianping","year":"2022","unstructured":"Tianping Zhang, Zheyu Zhang, Haoyan Luo, Fengyuan Liu, Wei Cao, and Jian Li. 2022. Openfe: Automated feature generation beyond expert-level performance. (2022)."}],"event":{"name":"CIKM '24: The 33rd ACM International Conference on Information and Knowledge Management","location":"Boise ID USA","acronym":"CIKM '24","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 33rd ACM International Conference on Information and Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3627673.3679153","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3627673.3679153","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:03:28Z","timestamp":1750291408000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3627673.3679153"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,21]]},"references-count":36,"alternative-id":["10.1145\/3627673.3679153","10.1145\/3627673"],"URL":"https:\/\/doi.org\/10.1145\/3627673.3679153","relation":{},"subject":[],"published":{"date-parts":[[2024,10,21]]},"assertion":[{"value":"2024-10-21","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}