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
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 48%lanl-ansi/MathOptAI.jl →
- LinkedLinked via arxiv author · 85%Zhuowei Chen →
“Neuron-Aware Active Few-Shot Learning for LLMs”
- LinkedLinked via arxiv author · 85%Liwei Chen →
“Neuron-Aware Active Few-Shot Learning for LLMs”
- LinkedLinked via arxiv author · 85%Christian Schunn →
“Neuron-Aware Active Few-Shot Learning for LLMs”
- LinkedLinked via arxiv author · 85%Raquel Coelho →
“Neuron-Aware Active Few-Shot Learning for LLMs”
- LinkedLinked via arxiv author · 85%Xiang Lorraine Li →
“Neuron-Aware Active Few-Shot Learning for LLMs”
- FuzzySimilar title/name (fuzzy) · 59%aymericdamien/TopDeepLearning →
“Fuzzy title match (0.73): “Neuron-Aware Active Few-Shot Learning for LLMs” ≈ “aymericdamien/TopDeepLearning””