In-Context Semi-Supervised Learning
This addresses the challenge of label scarcity in in-context learning for AI practitioners, offering foundational insights into representation learning.
The paper tackles the problem of in-context learning with Transformers in low-label settings by introducing in-context semi-supervised learning, showing that Transformers can leverage unlabeled context to improve performance, with marked gains in accuracy.
There has been significant recent interest in understanding the capacity of Transformers for in-context learning (ICL), yet most theory focuses on supervised settings with explicitly labeled pairs. In practice, Transformers often perform well even when labels are sparse or absent, suggesting crucial structure within unlabeled contextual demonstrations. We introduce and study in-context semi-supervised learning (IC-SSL), where a small set of labeled examples is accompanied by many unlabeled points, and show that Transformers can leverage the unlabeled context to learn a robust, context-dependent representation. This representation enables accurate predictions and markedly improves performance in low-label regimes, offering foundational insights into how Transformers exploit unlabeled context for representation learning within the ICL framework.