Guardado en:
Detalles Bibliográficos
Autores principales: Morehouse, Kirsten N., Swaroop, Siddharth, Pan, Weiwei
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2503.00093
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915180261146624
author Morehouse, Kirsten N.
Swaroop, Siddharth
Pan, Weiwei
author_facet Morehouse, Kirsten N.
Swaroop, Siddharth
Pan, Weiwei
contents The proliferation of LLM bias probes introduces three significant challenges: (1) we lack principled criteria for choosing appropriate probes, (2) we lack a system for reconciling conflicting results across probes, and (3) we lack formal frameworks for reasoning about when (and why) probe results will generalize to real user behavior. We address these challenges by systematizing LLM social bias probing using actionable insights from social sciences. We then introduce EcoLevels - a framework that helps (a) determine appropriate bias probes, (b) reconcile conflicting findings across probes, and (c) generate predictions about bias generalization. Overall, we ground our analysis in social science research because many LLM probes are direct applications of human probes, and these fields have faced similar challenges when studying social bias in humans. Based on our work, we suggest how the next generation of LLM bias probing can (and should) benefit from decades of social science research.
format Preprint
id arxiv_https___arxiv_org_abs_2503_00093
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Rethinking LLM Bias Probing Using Lessons from the Social Sciences
Morehouse, Kirsten N.
Swaroop, Siddharth
Pan, Weiwei
Computers and Society
Artificial Intelligence
Computation and Language
The proliferation of LLM bias probes introduces three significant challenges: (1) we lack principled criteria for choosing appropriate probes, (2) we lack a system for reconciling conflicting results across probes, and (3) we lack formal frameworks for reasoning about when (and why) probe results will generalize to real user behavior. We address these challenges by systematizing LLM social bias probing using actionable insights from social sciences. We then introduce EcoLevels - a framework that helps (a) determine appropriate bias probes, (b) reconcile conflicting findings across probes, and (c) generate predictions about bias generalization. Overall, we ground our analysis in social science research because many LLM probes are direct applications of human probes, and these fields have faced similar challenges when studying social bias in humans. Based on our work, we suggest how the next generation of LLM bias probing can (and should) benefit from decades of social science research.
title Rethinking LLM Bias Probing Using Lessons from the Social Sciences
topic Computers and Society
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2503.00093