Automated Annotation with Generative AI Requires Validation

TL;DR

This paper emphasizes the importance of validating generative AI models like GPT-4 for text annotation tasks, demonstrating a workflow and software to ensure reliable, task-specific performance in social science research.

Contribution

It introduces a validated workflow and software for using LLMs in automated annotation, highlighting the need for task-specific validation to ensure accuracy.

Findings

LLM performance varies significantly across datasets and tasks

Validation improves annotation reliability

Software streamlines LLM deployment for annotation

Abstract

Generative large language models (LLMs) can be a powerful tool for augmenting text annotation procedures, but their performance varies across annotation tasks due to prompt quality, text data idiosyncrasies, and conceptual difficulty. Because these challenges will persist even as LLM technology improves, we argue that any automated annotation process using an LLM must validate the LLM's performance against labels generated by humans. To this end, we outline a workflow to harness the annotation potential of LLMs in a principled, efficient way. Using GPT-4, we validate this approach by replicating 27 annotation tasks across 11 datasets from recent social science articles in high-impact journals. We find that LLM performance for text annotation is promising but highly contingent on both the dataset and the type of annotation task, which reinforces the necessity to validate on a task-by-task basis. We make available easy-to-use software designed to implement our workflow and streamline the deployment of LLMs for automated annotation.