Are Stated Reasoning Steps Causally Load-Bearing?

arXiv:2609.27038 · cs.AI · Submitted 2026-09-22 · Read on arXiv

cs.AI

Submitted: 2026-09-22

Updated: 2026-09-22

Terminology

• Activation Patching — 2× in this paper · explained in 2 episodes
• Alignment — 1× in this paper · explained in 1 episode
• Chain-of-Thought (CoT) — 1× in this paper · explained in 4 episodes
• Chain-of-Thought Prompting — 1× in this paper · explained in 2 episodes
• Interpretability — 1× in this paper · explained in 15 episodes
• Reasoning Traces — 1× in this paper · explained in 3 episodes
• Trace — 1× in this paper · explained in 2 episodes

Sources

• Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety
• Measuring Faithfulness in Chain-of-Thought Reasoning
• Bypassing the Rationale: Causal Auditing of Implicit Reasoning in Language Models
• When Reasoning Traces Become Performative: Step-Level Evidence that Chain-of-Thought Is an Imperfect Oversight Channel
• Breaking the Chain: A Causal Analysis of LLM Faithfulness to Intermediate Structures
• When Chain-of-Thought Fails, the Solution Hides in the Hidden States
• How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding
• Qwen3 Technical Report

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection