LEAP: LLM-powered End-to-end Automatic Library for Processing Social Science Queries on Unstructured Data

Download PDF

Abstract

Social scientists are increasingly interested in analyzing the seman-Social scientists are increasingly interested in analyzing the semantic information (e.g., emotion) of unstructured data (e.g., Tweets), where the semantic information is not natively present. Perform-where the semantic information is not natively present. Performing this analysis in a cost-efficient manner requires using machine learning (ML) models to extract the semantic information and sub-learning (ML) models to extract the semantic information and subsequently analyze the now structured data. However, this process remains challenging for domain experts. To demonstrate the challenges in social science analytics, we col-To demonstrate the challenges in social science analytics, we collect a dataset, QUIET-ML, of 120 real-world social science queries in natural language and their ground truth answers. Existing systems struggle with these queries since (1) they require selecting and ap-struggle with these queries since (1) they require selecting and applying ML models, and (2) more than a quarter of these queries are vague, making standard tools like natural language to SQL systems unsuited. To address these issues, we develop LEAP, an end-to-end library that answers social science queries in natural language with ML. LEAP filters vague queries to ensure that the answers are deter-ML. LEAP filters vague queries to ensure that the answers are deterministic and selects from internally supported and user-defined ML functions to extend the unstructured data to structured tables with necessary annotations. LEAP further generates and executes code to respond to these natural language queries. LEAP achieves a 100% pass @ 3 and 92% pass @ 1 on QUIET-ML, with a $1.06 average end-to-end cost, of which code generation costs $0.02.