2 papers
cs.CL2026
Mechanistic Evidence for Faithfulness Decay in Chain-of-Thought Reasoning
Donald Ye, Max Loffgren, Om Kotadia +2
Chain-of-Thought (CoT) explanations are widely used to interpret how language models solve complex problems, yet it remains unclear whether these step-by-step explanations reflect…
cs.LG2026
Hidden Heroes and Gradient Bloats: Layer-Wise Redundancy Inverts Attribution in Transformers
Donald Ye
Gradient-based attribution is the workhorse of mechanistic interpretability, yet whether it reliably tracks causal importance at the component level remains largely untested. We ca…