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

2026-08-31

AI Summary

本文提出LCoT-GV，一种基于图注意网络的方法，用于验证大型语言模型中长推理链的正确性，通过将推理步骤表示为图结构来识别其中的逻辑错误。

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.

Problem

• Long Chains-of-Thought
• Reasoning Steps
• Contradictions
• Unsupported Inferences
• Irrelevant Steps

Innovation

• Graph Attention Networks
• Long Chain-of-Thought
• Reasoning Graphs
• Verification Dataset