Neuron-Aware Active Few-Shot Learning for LLMs

Zhuowei Chen, Liwei Chen, Christian Schunn, Raquel Coelho, Xiang Lorraine Li|July 2, 2026arXiv

Key Takeaway

Using internal neuron activation patterns to select few-shot examples is more effective than traditional output-based signals, helping identify what the model actually struggles with rather than just guessing from its outputs.

Summary

This paper proposes NeuFS, a method for selecting the most useful examples to annotate when adapting large language models to specialized tasks.

training efficiency evaluation

Key Terms

few-shot-learning active-learning neuron-activation hallucination semantic-similarity