The term “reasoning” itself is so misleading. “Generating a dozen of intermediate tokens before answering”, seems more like “context injection” rather than “ability to reason”
Slides for my lecture “LLM Reasoning” at Stanford CS 25: dennyzhou.github.io/LLM-Reasoning-…
Key points:
1. Reasoning in LLMs simply means generating a sequence of intermediate tokens before producing the final answer. Whether this resembles human reasoning is irrelevant. The crucial
