In Context Semi-Supervised Learning
Jiashuo Fan, Paul Rosu, Aaron T Wang, Lawrence Carin, Xiang Cheng
Abstract
There has been significant recent interest on 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. Our code is available at https://github.com/Jason-fan20/ICL_Semi.
BibTeX
@inproceedings{
fan2026in,
title={In Context Semi-Supervised Learning},
author={Jiashuo Fan and Paul Rosu and Aaron T Wang and Lawrence Carin and Xiang Cheng},
booktitle={The Fourteenth International Conference on Learning Representations},
year={2026},
url={https://openreview.net/forum?id=lqrpmqrTnH}
}