In-context learning in presence of spurious correlations

Hrayr Harutyunyan, Rafayel Darbinyan, Samvel Karapetyan, Hrant Khachatrian

Keywords: in-context learning, spurious features, out-of-distribution, meta learning

TL;DR: This work explores the possibility of training an in-context learner for classification tasks involving spurious features.

Abstract:

Large language models exhibit a remarkable capacity for in-context learning, where they learn to solve tasks given a few examples.
Recent work has shown that transformers can be trained to perform simple regression tasks in-context.
This work explores the possibility of training an in-context learner for classification tasks involving spurious features.
We find that the conventional approach of training in-context learners is susceptible to spurious features.
Moreover, when the meta-training dataset includes instances of only one task, the conventional approach leads to task memorization and fails to produce a model that leverages context for predictions.
Based on these observations, we propose a novel technique to train such a learner for a given classification task.
Remarkably, this in-context learner matches and sometimes outperforms strong methods like ERM and GroupDRO.
However, unlike these algorithms, it does not generalize well to other tasks.
We show that it is possible to obtain an in-context learner that generalizes to unseen tasks by training on a diverse dataset of synthetic in-context learning instances.

Primary Area: transfer learning, meta learning, and lifelong learning

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 10738