Interpretable Traces, Unexpected Outcomes: Investigating the Disconnect in Trace-Based Knowledge Distillation

Understand

Recent advances in reasoning-focused Large Language Models (LLMs) have introduced Chain-of-Thought (CoT) traces - intermediate reasoning steps generated before a final answer.

• These traces, as in DeepSeek R1, guide inference and train smaller models.
• A common but under-examined assumption is that these traces are both semantically correct and interpretable to end-users.
• While intermediate reasoning steps are believed to improve accuracy, we question whether they are actually valid and understandable.