CAP scores attention heads via interventional masking on reasoning calibration data and converts those scores into weight pruning decisions, reporting up to 61% relative accuracy gains over Wanda at 20% sparsity on ARC-Challenge.
X-pruner: explainable pruning for vision transformers.arXiv preprint arXiv:2303.04935,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Pruning via Causal Attribution Preserves Reasoning Performance in Large Language Models
CAP scores attention heads via interventional masking on reasoning calibration data and converts those scores into weight pruning decisions, reporting up to 61% relative accuracy gains over Wanda at 20% sparsity on ARC-Challenge.