LCoT-GV: Graph Attention Networks for Verifying Long Reasoning Chains in Large Language Models

arXiv:2608.30679 · cs.CL, cs.AI · Submitted 2026-08-31 · Read on arXiv

cs.CL, cs.AI

Submitted: 2026-08-31

Updated: 2026-08-31

Comments: 6 pages without references, 2 tables, 1 algorithm, 1 figure

Code: https://github.com/ormarv/LCoT-GV

License: http://creativecommons.org/licenses/by-sa/4.0/

The gist: Large Reasoning Models produce Long Chains-of-Thought (LCoTs) which involve breaking down the problem into smaller reasoning steps before reaching the conclusion.

Terminology

Abstract

Large Reasoning Models produce Long Chains-of-Thought (LCoTs) which involve breaking down the problem into smaller reasoning steps before reaching the conclusion. However, these steps often contain contradictions, unsupported inferences, or irrelevant steps, even when the final answer is correct. We propose Long Chain-of-Thought Graph Verifier (LCoT-GV), a graph-based framework that represents LCoTs as reasoning graphs. Each node in the graph represents a reasoning step and the edges encode semantic and logical relations. A Graph Attention Network is then trained to predict chain-of-thought correctness from the reasoning graph. We construct a new graph-oriented verification dataset from multiple reasoning benchmarks for question answering in various domains. The results show that our method is competitive with the most similar approaches.

Sources

Related papers