Position: Rethinking LLM Bias Probing Using Lessons from the Social Sciences

Kirsten Morehouse, Siddharth Swaroop, Weiwei Pan
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:81841-81860, 2025.

Abstract

The proliferation of LLM bias probes introduces three challenges: we lack (1) principled criteria for selecting appropriate probes, (2) a system for reconciling conflicting results across probes, and (3) formal frameworks for reasoning about when and why experimental findings will generalize to real user behavior. In response, we propose a systematic approach to LLM social bias probing, drawing on insights from the social sciences. Central to this approach is EcoLevels—a novel framework that helps (a) identify appropriate bias probes (b) reconcile conflicting results, and (c) generate predictions about bias generalization. We ground our framework in the social sciences, as many LLM probes are adapted from human studies, and these fields have faced similar challenges when studying bias in humans. Finally, we outline five lessons that demonstrate how LLM bias probing can (and should) benefit from decades of social science research

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-morehouse25a, title = {Position: Rethinking {LLM} Bias Probing Using Lessons from the Social Sciences}, author = {Morehouse, Kirsten and Swaroop, Siddharth and Pan, Weiwei}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {81841--81860}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/morehouse25a/morehouse25a.pdf}, url = {https://proceedings.mlr.press/v267/morehouse25a.html}, abstract = {The proliferation of LLM bias probes introduces three challenges: we lack (1) principled criteria for selecting appropriate probes, (2) a system for reconciling conflicting results across probes, and (3) formal frameworks for reasoning about when and why experimental findings will generalize to real user behavior. In response, we propose a systematic approach to LLM social bias probing, drawing on insights from the social sciences. Central to this approach is EcoLevels—a novel framework that helps (a) identify appropriate bias probes (b) reconcile conflicting results, and (c) generate predictions about bias generalization. We ground our framework in the social sciences, as many LLM probes are adapted from human studies, and these fields have faced similar challenges when studying bias in humans. Finally, we outline five lessons that demonstrate how LLM bias probing can (and should) benefit from decades of social science research} }
Endnote
%0 Conference Paper %T Position: Rethinking LLM Bias Probing Using Lessons from the Social Sciences %A Kirsten Morehouse %A Siddharth Swaroop %A Weiwei Pan %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-morehouse25a %I PMLR %P 81841--81860 %U https://proceedings.mlr.press/v267/morehouse25a.html %V 267 %X The proliferation of LLM bias probes introduces three challenges: we lack (1) principled criteria for selecting appropriate probes, (2) a system for reconciling conflicting results across probes, and (3) formal frameworks for reasoning about when and why experimental findings will generalize to real user behavior. In response, we propose a systematic approach to LLM social bias probing, drawing on insights from the social sciences. Central to this approach is EcoLevels—a novel framework that helps (a) identify appropriate bias probes (b) reconcile conflicting results, and (c) generate predictions about bias generalization. We ground our framework in the social sciences, as many LLM probes are adapted from human studies, and these fields have faced similar challenges when studying bias in humans. Finally, we outline five lessons that demonstrate how LLM bias probing can (and should) benefit from decades of social science research
APA
Morehouse, K., Swaroop, S. & Pan, W.. (2025). Position: Rethinking LLM Bias Probing Using Lessons from the Social Sciences. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:81841-81860 Available from https://proceedings.mlr.press/v267/morehouse25a.html.

Related Material