CLAIJul 18, 2022

Selection Bias Induced Spurious Correlations in Large Language Models

arXiv:2207.08982v112 citationsh-index: 7
Originality Incremental advance
AI Analysis

This highlights a critical bias issue in LLMs that can affect fairness and reliability in NLP applications.

The paper demonstrates that large language models (LLMs) learn spurious correlations between gender pronouns and neutral variables like date and location due to dataset selection bias, using a masked gender task on pre-trained BERT and RoBERTa models.

In this work we show how large language models (LLMs) can learn statistical dependencies between otherwise unconditionally independent variables due to dataset selection bias. To demonstrate the effect, we developed a masked gender task that can be applied to BERT-family models to reveal spurious correlations between predicted gender pronouns and a variety of seemingly gender-neutral variables like date and location, on pre-trained (unmodified) BERT and RoBERTa large models. Finally, we provide an online demo, inviting readers to experiment further.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes