Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhang, Bolun, Li, Linzhuo, Chen, Yunqi, Zhao, Qinlin, Zhu, Zihan, Yi, Xiaoyuan, Xie, Xing
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2512.05461
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911304084619264
author Zhang, Bolun
Li, Linzhuo
Chen, Yunqi
Zhao, Qinlin
Zhu, Zihan
Yi, Xiaoyuan
Xie, Xing
author_facet Zhang, Bolun
Li, Linzhuo
Chen, Yunqi
Zhao, Qinlin
Zhu, Zihan
Yi, Xiaoyuan
Xie, Xing
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2512_05461
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Knowing Your Uncertainty -- On the application of LLM in social sciences
Zhang, Bolun
Li, Linzhuo
Chen, Yunqi
Zhao, Qinlin
Zhu, Zihan
Yi, Xiaoyuan
Xie, Xing
Computers and Society
Artificial Intelligence
Human-Computer Interaction
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.
title Knowing Your Uncertainty -- On the application of LLM in social sciences
topic Computers and Society
Artificial Intelligence
Human-Computer Interaction
url https://arxiv.org/abs/2512.05461