ICE-SEARCH: A Language Model-Driven Feature Selection Approach

arXiv:2402.18609v1 Announce Type: new
Abstract: This study unveils the In-Context Evolutionary Search (ICE-SEARCH) method, the first work that melds language models (LMs) with evolutionary algorithms for feature selection (FS) tasks and demonstrates its effectiveness in Medical Predictive Analytics (MPA) applications. ICE-SEARCH harnesses the crossover and mutation capabilities inherent in LMs within an evolutionary framework, significantly improving FS through the model's comprehensive world knowledge and its adaptability to a variety of roles. Our evaluation of this methodology spans three crucial MPA …

abstract algorithms analytics applications arxiv capabilities context cs.ai cs.lg evolutionary algorithms feature feature selection ice language language model language models lms medical mutation predictive predictive analytics search study tasks type work