Out-of-Context Reasoning in LLMs: A short primer and reading list

For the full primer and reading list, visit outofcontextreasoning.com.

What is out-of-context reasoning for LLMs?

Out-of-context reasoning (OOCR) is a concept relevant to LLM generalization and AI alignment.

It’s when an LLM reaches a conclusion that requires non-trivial reasoning but the reasoning is not present in the context window. The reasoning could instead take place in the forward pass or during the training process. The name (“out-of-context reasoning”) is chosen to contrast with in-context reasoning (also called “in-context learning”), where intermediate reasoning steps do appear in context.

Visit outofcontextreasoning.com for a comprehensive primer on OOCR, including key research papers, examples, and implications for AI safety.