Neuron-Aware Active Few-Shot Learning for LLMs
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-S
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
- Linked via arxiv authorZhuowei Chen →
Neuron-Aware Active Few-Shot Learning for LLMs
- Linked via arxiv authorLiwei Chen →
Neuron-Aware Active Few-Shot Learning for LLMs
- Linked via arxiv authorChristian Schunn →
Neuron-Aware Active Few-Shot Learning for LLMs
- Linked via arxiv authorRaquel Coelho →
Neuron-Aware Active Few-Shot Learning for LLMs
- Linked via arxiv authorXiang Lorraine Li →
Neuron-Aware Active Few-Shot Learning for LLMs