AttriCoT is a black-box algorithm that attributes causal importance to units in a specific CoT trace via a structural causal model estimated with linear forward passes.
Title resolution pending
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
-
Local Causal Attribution of Chain-of-Thought Reasoning
AttriCoT is a black-box algorithm that attributes causal importance to units in a specific CoT trace via a structural causal model estimated with linear forward passes.