Incubating Text Classifiers Following User Instruction with Nothing but LLM

arXiv:2404.10877v1 Announce Type: new
Abstract: In this paper, we aim to generate text classification data given arbitrary class definitions (i.e., user instruction), so one can train a small text classifier without any human annotation or raw corpus. Compared with pioneer attempts, our proposed Incubator is the first framework that can handle complicated and even mutually dependent classes (e.g., "TED Talk given by Educator" and "Other"). Specifically, Incubator is an LLM firstly tuned on the instruction-to-data mappings that we obtained from …

abstract aim annotation arxiv class classification classifier classifiers cs.cl data definitions framework generate human incubating llm nothing paper raw small text text classification train type