From Decorative to Load-Bearing: Task Difficulty Shapes the Causal Role of Chain-of-Thought
arXiv:2609.25366v1 Announce Type: new Abstract: Chain-of-thought (CoT) monitoring is only meaningful if written reasoning causally constrains the answer. We introduce continuation-based causal testing, an ablation-patch intervention that perturbs one reasoning step, truncates the chain, and forces…
Read the full story at arXiv cs.AI ↗
Timeline · 1 report
- 2026-09-24 04:00 · arXiv cs.AI
From Decorative to Load-Bearing: Task Difficulty Shapes the Causal Role of Chain-of-Thought