In-context Learning in Presence of Spurious Correlations

TMLR Paper6125 Authors

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 in-weights learning 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.

Submission Length: Regular submission (no more than 12 pages of main content)

Previous TMLR Submission Url: https://openreview.net/forum?id=ZC5bJ8B2vH

Changes Since Last Submission: Previous submission was desk rejected because we had used \usepackage[notes=true, done=false, later=true]{dtrt}, causing omission of the text "Under review as submission to TMLR" at the top of every page. The current submission fixes this issues and is otherwise identical.

Assigned Action Editor: ~Amit_Sharma3

Submission Number: 6125