Exploiting Selection Bias on Underspecified Tasks in Large Language Models

In this paper we motivate the causal mechanisms behind sample selection induced collider bias (selection collider bias) that can cause Large Language Models (LLMs) to learn unconditional dependence between entities that are unconditionally independent in the real world. We show that selection collider bias can become amplified in underspecified learning tasks, and although difficult to overcome, we describe a method to exploit the resulting spurious correlations for determination of when a model may be uncertain about its prediction. We demonstrate an uncertainty metric that matches human uncertainty in tasks with gender pronoun underspecification on an extended version of the Winogender Schemas evaluation set, and we provide online demos where users can evaluate spurious correlations and apply our uncertainty metric to their own texts and models. Finally, we generalize our approach to address a wider range of prediction tasks.

Selection Collider Bias in Large Language Models

In this paper we motivate the causal mechanisms behind sample selection induced collider bias (selection collider bias) that can cause Large Language Models (LLMs) to learn unconditional dependence between entities that are unconditionally independent in the real world. We show that selection collider bias can be amplified in underspecified learning tasks, and that the magnitude of the resulting spurious correlations appear scale agnostic. While selection collider bias can be difficult to overcome, we describe a method to exploit the resulting spurious correlations for determination of when a model may be uncertain about its prediction, and demonstrate that it matches human uncertainty in tasks with gender pronoun underspecification on an extended version of the Winogender Schemas evaluation set.

Selection Bias Induced Spurious Correlations in Large Language 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.