Attribution-guided pruning with contrastive relevance identifies behavior-specific circuits in small LLMs and removes as little as 0.03-0.3% of components to reduce toxicity or repetition while preserving general performance.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2025 2representative citing papers
InFOM applies flow matching to model intention-conditioned occupancy measures for RL pre-training, reporting 1.8x median return gains and 36% higher success rates on benchmarks.
citing papers explorer
-
Attribution-Guided Pruning for Insight and Control: Circuit Discovery and Targeted Correction in Small-scale LLMs
Attribution-guided pruning with contrastive relevance identifies behavior-specific circuits in small LLMs and removes as little as 0.03-0.3% of components to reduce toxicity or repetition while preserving general performance.
-
Intention-Conditioned Flow Occupancy Models
InFOM applies flow matching to model intention-conditioned occupancy measures for RL pre-training, reporting 1.8x median return gains and 36% higher success rates on benchmarks.