A unified multi-component causal tracing method that uses soft interventions and a metric transformation to efficiently select critical LLM components for a target performance metric.
Integrated Directional Gradients: Feature Interaction Attribution for Neural NLP Models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Multi-component Causal Tracing in Large Language Models
A unified multi-component causal tracing method that uses soft interventions and a metric transformation to efficiently select critical LLM components for a target performance metric.