Verifying Chain-of-Thought Reasoning via its Computational Graph

ICLR 2026 Conference Submission13079 Authors

Keywords: Mechanistic Interpretability, Chain-of-Thought Reasoning, Attribution Graphs

TL;DR: We introduce CRV, a white-box methodology that treats attribution graphs as execution traces, and use it to provide evidence that flawed reasoning has a verifiable computational structure.

Abstract: Current Chain-of-Thought (CoT) verification methods predict reasoning correctness based on outputs (black-box) or activations (gray-box), but offer limited insight into \textit{why} a computation fails. We introduce a white-box method: \textbf{Circuit-based Reasoning Verification (CRV)}. We hypothesize that attribution graphs of correct CoT steps, viewed as \textit{execution traces} of the model's latent reasoning circuits, possess distinct structural fingerprints from those of incorrect steps. By training a classifier on structural features of these graphs, we show that these traces contain a powerful signal of reasoning errors. Our white-box approach yields novel scientific insights unattainable by other methods. (1) We demonstrate that structural signatures of error are highly predictive, establishing the viability of verifying reasoning directly via its computational graph. (2) We find these signatures to be highly domain-specific, revealing that failures in different reasoning tasks manifest as distinct computational patterns. (3) We provide evidence that these signatures are not merely correlational; by using our analysis to guide targeted interventions on individual transcoder features, we successfully correct the model's faulty reasoning. Our work shows that, by scrutinizing a model's computational process, we can move from simple error detection to a deeper, causal understanding of LLM reasoning.

Primary Area: interpretability and explainable AI

Submission Number: 13079