Large Language Models Can be Lazy Learners: Analyze Shortcuts in In-Context Learning

TL;DR

This paper investigates how large language models rely on shortcuts in prompts during in-context learning, revealing that larger models are more prone to exploiting spurious correlations, which impacts robustness and reliability.

Contribution

It uncovers the tendency of LLMs to use shortcuts in prompts and shows that larger models are more likely to do so, highlighting new challenges for robustness evaluation.

Findings

LLMs exploit shortcuts in prompts for downstream tasks.

Larger models are more prone to using shortcuts during inference.

Shortcuts impact the robustness and reliability of in-context learning.

Abstract

Large language models (LLMs) have recently shown great potential for in-context learning, where LLMs learn a new task simply by conditioning on a few input-label pairs (prompts). Despite their potential, our understanding of the factors influencing end-task performance and the robustness of in-context learning remains limited. This paper aims to bridge this knowledge gap by investigating the reliance of LLMs on shortcuts or spurious correlations within prompts. Through comprehensive experiments on classification and extraction tasks, we reveal that LLMs are "lazy learners" that tend to exploit shortcuts in prompts for downstream tasks. Additionally, we uncover a surprising finding that larger models are more likely to utilize shortcuts in prompts during inference. Our findings provide a new perspective on evaluating robustness in in-context learning and pose new challenges for detecting and mitigating the use of shortcuts in prompts.