HomeResearch LibraryFaithful Reasoning Using Large Language Models
system architectureChapter 3arXiv · 2022

Faithful Reasoning Using Large Language Models

Antonia Creswell (DeepMind), Murray Shanahan (DeepMind)

Abstract

We present a method for faithful reasoning with LLMs that produces verifiable reasoning chains. The approach separates reasoning into selection and inference steps, enabling verification of each step.

Eigenvector Insight — Zone III / PASF-PADE AnalysisNot part of the original paper
Eigenvector Research — Marco van Hurne
How this paper contributes to solving the Zone III problem (PASF-PADE)

Faithful reasoning — where the stated reasoning actually causes the conclusion — is essential for enterprise governance. Zone III agents must not only produce correct outputs but must do so through verifiable reasoning chains that can be audited.

Why AI is not sufficient for Zone III without this

Zone III refers to high-complexity, high-risk, long-running agentic workflows — the class of enterprise AI deployments where a single failure can cascade across hundreds of steps. Standard AI models, trained to predict the next token, are not inherently designed for durable, governed, multi-step execution. This paper addresses one or more of the structural gaps that make Zone III deployments unsafe without explicit architectural intervention.

Key Contributions

  • →Selection-inference reasoning
  • →Verifiable reasoning chains
  • →Faithful reasoning methodology

Topics

faithful reasoningverifiable reasoningreasoning chainsinterpretability