Towards a Mechanistic Understanding of Propositional Logical Reasoning in Large Language Models

The paper investigates how large language models perform propositional logical reasoning by conducting a causal mechanistic analysis on the PropLogic-MI benchmark. It identifies four interlocking mechanisms—Staged Computation, Information Transmission, Fact Retrospection, and Specialized Attention Heads—that organize the reasoning process across layers. The study demonstrates that these mechanisms recur across different model families, rule categories, and reasoning hops, indicating a structured, layer‑organized internal process for propositional reasoning.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• llms
• benchmarks