Neuron-Aware Active Few-Shot Learning for LLMs

ACL ARR 2026 January Submission8174 Authors

Keywords: Active Learning, Neuron Analysis, Data Selection, Few-shot Learning

Abstract: Active Few-Shot Learning (AFSL) adapts LLMs to specialized domains by identifying the most valuable unlabeled samples for annotation and use as few-shot demonstrations, effectively reducing human annotation costs while promoting high performance. However, existing methods typically rely on output-level signals for the sample identification, such as predictive entropy or semantic similarities with test-time data based on external embeddings, which often overlook models' internal dynamics which could pinpoint specific knowledge gaps. To bridge this gap, we propose **NeuFS**, a **Neu**ron-Aware Active **F**ew-**S**hot Learning framework that shifts the selection paradigm from output-level proxies to models' internal dynamics. **NeuFS** utilizes neuron activation patterns to represent sample directly, and includes a dual-criteria selection strategy that: (1) ensures few-shot sample diversity with neuron patterns for broader example coverage, while (2) prioritizing on identifying informative and challenging few-shot samples LLMs tend to hallucinate by quantifying *neuron consensus*. Experiments on three datasets demonstrate that NeuFS excels in both reasoning and text classification tasks, outperforming existing AFSL baselines. Ablation studies further highlight that internal neuron activations provide a more principled and effective selection signal than external embeddings, validating the superiority of the proposed NeuFS.

Paper Type: Long

Research Area: Low-resource Methods for NLP

Research Area Keywords: Active Learning, Interpretability, Few-shot Learning, Data Selection, Neuron Analysis

Contribution Types: Approaches to low-resource settings, Approaches low compute settings-efficiency

Languages Studied: English

Submission Number: 8174