Knowing Your Uncertainty -- On the application of LLM in social sciences

TL;DR

This paper emphasizes the importance of explicit uncertainty assessment when applying large language models to social sciences, proposing a unified framework to evaluate LLM uncertainty across task and validation types.

Contribution

It introduces a T-V typology for classifying uncertainty quantification methods, bridging social science and computer science perspectives for rigorous LLM application.

Findings

Mapped existing UQ methods to the T-V typology

Provided practical guidelines for social science researchers

Highlighted the need for uncertainty assessment in LLM use

Abstract

Large language models (LLMs) are rapidly being integrated into computational social science research, yet their blackboxed training and designed stochastic elements in inference pose unique challenges for scientific inquiry. This article argues that applying LLMs to social scientific tasks requires explicit assessment of uncertainty-an expectation long established in both quantitative methodology in the social sciences and machine learning. We introduce a unified framework for evaluating LLM uncertainty along two dimensions: the task type (T), which distinguishes between classification, short-form, and long-form generation, and the validation type (V), which captures the availability of reference data or evaluative criteria. Drawing from both computer science and social science literature, we map existing uncertainty quantification (UQ) methods to this T-V typology and offer practical recommendations for researchers. Our framework provides both a methodological safeguard and a practical guide for integrating LLMs into rigorous social science research.