LLM-Measure: Generating Valid, Consistent, and Reproducible Text-Based Measures for Social Science Research

TL;DR

This paper introduces a novel approach using large language models' internal states to generate valid, consistent, and reproducible text-based measures for social science research, addressing the need for reliable concept quantification from text data.

Contribution

It proposes a new method that learns concept vectors from LLMs' hidden states to produce standardized measures, improving validity and reproducibility in social science text analysis.

Findings

Method produces highly valid measures across studies

Ensures consistency and reproducibility in concept estimation

Applicable across diverse social science contexts

Abstract

The increasing use of text as data in social science research necessitates the development of valid, consistent, reproducible, and efficient methods for generating text-based concept measures. This paper presents a novel method that leverages the internal hidden states of large language models (LLMs) to generate these concept measures. Specifically, the proposed method learns a concept vector that captures how the LLM internally represents the target concept, then estimates the concept value for text data by projecting the text's LLM hidden states onto the concept vector. Three replication studies demonstrate the method's effectiveness in producing highly valid, consistent, and reproducible text-based measures across various social science research contexts, highlighting its potential as a valuable tool for the research community.