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.
Generating Hierarchical Explanations on Text Classification via Feature Interaction Detection
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Shapley values for LLM explanations in financial text are shown via theory and experiments to produce attributions consistent with financial reasoning.
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.