English

Uncovering Implicit Bias in Large Language Models with Concept Learning Dataset

Computation and Language 2025-11-27 v2 Artificial Intelligence

Abstract

We introduce a dataset of concept learning tasks that helps uncover implicit biases in large language models. Using in-context concept learning experiments, we found that language models may have a bias toward upward monotonicity in quantifiers; such bias is less apparent when the model is tested by direct prompting without concept learning components. This demonstrates that in-context concept learning can be an effective way to discover hidden biases in language models.

Keywords

Cite

@article{arxiv.2510.01219,
  title  = {Uncovering Implicit Bias in Large Language Models with Concept Learning Dataset},
  author = {Leroy Z. Wang},
  journal= {arXiv preprint arXiv:2510.01219},
  year   = {2025}
}

Comments

Presented at EurIPS 2025 Workshop - Unifying Perspectives on Learning Biases (UPLB) https://sites.google.com/view/towards-a-unified-view

R2 v1 2026-07-01T06:11:24.040Z