Transforming unstructured text into structured and meaningful forms, organized by useful category labels, is a fundamental step in text mining for downstream analysis and application. However, most existing methods for producing label taxonomies and building text-based label classifiers still rely heavily on domain expertise and manual curation, making the process expensive and time-consuming. This is particularly challenging when the label space is under-specified and large-scale data annotations are unavailable. In this paper, we address these challenges with Large Language Models (LLMs), whose prompt-based interface facilitates the induction and use of large-scale pseudo labels. We propose TnT-LLM, a two-phase framework that employs LLMs to automate the process of end-to-end label generation and assignment with minimal human effort for any given use-case. In the first phase, we introduce a zero-shot, multi-stage reasoning approach which enables LLMs to produce and refine a label taxonomy iteratively. In the second phase, LLMs are used as data labelers that yield training samples so that lightweight supervised classifiers can be reliably built, deployed, and served at scale. We apply TnT-LLM to the analysis of user intent and conversational domain for Bing Copilot (formerly Bing Chat), an open-domain chat-based search engine. Extensive experiments using both human and automatic evaluation metrics demonstrate that TnT-LLM generates more accurate and relevant label taxonomies when compared against state-of-the-art baselines, and achieves a favorable balance between accuracy and efficiency for classification at scale.
The timing, amount, and quality of sleep are critical for an individual’s health and quality of life. This paper provides a focused narrative review of the existing literature around multidimensional environments and sleep health for aging adults. Five electronic databases, Scopus, Web of Science, PubMed/Medline; EBSCOhost, PsycINFO (ProQuest), and Google Scholar yielded 54,502 total records. After removing duplicates, non-peer reviewed academic articles, and nonrelevant articles, 70 were included for review. We were able to categorize environmental factors into housing security, home environment, and neighborhood environment, and, within each environmental category, specific elements/aspects are discussed. This paper provides a comprehensive map connecting identified levels of influence (individual, home/house, and neighborhood-level) in which subfactors are listed under each level of influence/category with the related literature list. Our review highlights that multidimensional environmental factors can affect aging adults’ sleep health and eventually their physical, mental, and cognitive health and that sleep disparities exist in racial minorities in socioeconomically disadvantaged communities in which cumulative environmental stressors coexist. Based on this focused narrative review on the multidimensional sleep environments for aging adults, knowledge gaps are identified, and future research directions are suggested.