In-context learning (ICL) has emerged as a successful paradigm for leveraging large language models (LLMs). However, it often struggles to generalize beyond the distribution of the provided demonstrations. A recent advancement in enhancing robustness is ICL with explanations (X-ICL), which improves prediction reliability by guiding LLMs to understand and articulate the reasoning behind correct labels. Building on this approach, we introduce an advanced framework that extends X-ICL by systematically exploring explanations for all possible labels (X²-ICL), thereby enabling more comprehensive and robust decision-making. Experimental results on multiple natural language understanding datasets validate the effectiveness of X²-ICL, demonstrating significantly improved robustness to out-of-distribution data compared to the existing ICL approaches.

Recent models for natural language understanding are inclined to exploit simple patterns in datasets, commonly known as shortcuts. These shortcuts hinge on spurious correlations between labels and latent features existing in the training data. At inference time, shortcut-dependent models are likely to generate erroneous predictions under distribution shifts, particularly when some latent features are no longer correlated with the labels. To avoid this, previous studies have trained models to eliminate the reliance on shortcuts. In this study, we explore a different direction: pessimistically aggregating the predictions of a mixture-of-experts, assuming each expert captures relatively different latent features. The experimental results demonstrate that our post-hoc control over the experts significantly enhances the model’s robustness to the distribution shift in shortcuts. Additionally, we show that our approach has some practical advantages. We also analyze our model and provide results to support the assumption.1