Search papers, labs, and topics across Lattice.
This paper introduces NeuFS, a Neuron-Aware Active Few-Shot Learning framework that enhances the selection of unlabeled samples for annotation by leveraging internal neuron activation patterns of large language models (LLMs). By shifting the focus from traditional output-level signals to internal dynamics, NeuFS employs a dual-criteria selection strategy that ensures diversity in few-shot samples while identifying the most informative ones that LLMs often misinterpret. Experimental results across three datasets show that NeuFS significantly outperforms existing AFSL methods in both reasoning and text classification tasks, validating the importance of internal neuron activations in sample selection.
Shifting the focus to internal neuron dynamics reveals that LLMs can be better adapted to specialized domains with fewer, more informative examples.
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 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 Neuron-Aware Active Few-Shot 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.
