Mitigating Copy Bias in In-Context Learning through Neuron Pruning

ACL ARR 2025 May Submission433 Authors

Abstract:

Large language models (LLMs) have demonstrated impressive few-shot in-context learning (ICL) abilities. Still, we show that they are sometimes prone to a `copying bias', where they copy answers from provided examples instead of learning the underlying patterns. In this work, we propose a novel and simple method to mitigate such copying bias. First, we create a synthetic task and use the Integrated Gradients method to identify neurons that prioritize copying over generalization. We demonstrate that pruning these neurons consistently improves performance across a diverse set of ICL tasks, including both single-token and multi-token scenarios, while maintaining or even improving the model's general capabilities. We also show that our method is applicable across various LLM architectures, including Transformers and State-Space Models, without requiring modifications.
In our analysis, we adopt a task-recognition perspective on ICL and examine task vectors (Hendel et al., 2023) induced by the model. We find that pruning enhances the quality of these vectors, suggesting that the pruned neurons previously hindered effective task recognition.

Paper Type: Long

Research Area: Interpretability and Analysis of Models for NLP

Research Area Keywords: in context learning,interpretability,memorization

Contribution Types: Model analysis & interpretability

Languages Studied: english

Submission Number: 433