Exploring Explanations Improves the Robustness of In-Context Learning
By: Ukyo Honda, Tatsushi Oka
Potential Business Impact:
Helps computers make better guesses by explaining why.
In-context learning (ICL) has emerged as a successful paradigm for leveraging large language models (LLMs). However, it often struggles to generalize beyond the distribution of the provided demonstrations. A recent advancement in enhancing robustness is ICL with explanations (X-ICL), which improves prediction reliability by guiding LLMs to understand and articulate the reasoning behind correct labels. Building on this approach, we introduce an advanced framework that extends X-ICL by systematically exploring explanations for all possible labels (X$^2$-ICL), thereby enabling more comprehensive and robust decision-making. Experimental results on multiple natural language understanding datasets validate the effectiveness of X$^2$-ICL, demonstrating significantly improved robustness to out-of-distribution data compared to the existing ICL approaches.
Similar Papers
Leveraging In-Context Learning for Language Model Agents
Computation and Language
Helps AI agents learn by watching examples.
On the Relationship Between the Choice of Representation and In-Context Learning
Computation and Language
Lets computers learn new things better.
Corrective In-Context Learning: Evaluating Self-Correction in Large Language Models
Computation and Language
Teaches computers to fix their own mistakes.