{"type":"ScholarlyArticle","title":"Dynamic and Adaptive Feature Generation with LLM","authors":[{"name":"Xinhao Zhang","slug":"xinhao-zhang","given":"Xinhao","family":"Zhang","affiliation":""},{"name":"Jinghan Zhang","slug":"jinghan-zhang","given":"Jinghan","family":"Zhang","affiliation":""},{"name":"Banafsheh Rekabdar","slug":"banafsheh-rekabdar","given":"Banafsheh","family":"Rekabdar","affiliation":""},{"name":"Yuanchun Zhou","slug":"yuanchun-zhou","given":"Yuanchun","family":"Zhou","affiliation":""},{"name":"Pengfei Wang","slug":"pengfei-wang","given":"Pengfei","family":"Wang","affiliation":""},{"name":"Kunpeng Liu","slug":"kunpeng-liu","given":"Kunpeng","family":"Liu","affiliation":""}],"abstract":"The representation of feature space is a crucial environment where data points get vectorized and embedded for subsequent modeling. Thus, the efficacy of machine learning (ML) algorithms is closely related to the quality of feature engineering. As one of the most important techniques, feature generation transforms raw data into an optimized feature space conducive to model training and further refines the space. Despite the advancements in automated feature engineering and feature generation, current methodologies often suffer from three fundamental issues: lack of explainability, limited applicability, and inflexible strategy. These shortcomings frequently hinder and limit the deployment of ML models across varied scenarios. Our research introduces a novel approach adopting large language models (LLMs) and feature-generating prompts to address these challenges. We propose a dynamic and adaptive feature generation method that enhances the interpretability of the feature generation process. Our approach broadens the applicability across various data types and tasks and offers advantages in terms of strategic flexibility. A broad range of experiments showcases that our approach is significantly superior to existing methods.","doi":"10.24963/ijcai.2025/782","url":"https://ijcai.org/proceedings/2025/782","pdf":"https://ijcai.org/proceedings/2025/0782.pdf","markdown":"https://ijcai.org/proceedings/2025/782.md","bibtex":"https://ijcai.org/proceedings/2025/bibtex/782","volume":{"slug":"2025","title":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2025","url":"https://ijcai.org/proceedings/2025/","year":2025,"location":"Montreal, Canada","dates":"16-22 August 2025","editors":"James Kwok","isbn":"978-1-956792-06-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2025"},"section":"Machine Learning","track":"Main Track","number":782,"pages":{"first":7029,"last":7037},"keywords":["Machine Learning: ML: Feature extraction, selection and dimensionality reduction"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}