arXiv：cs.AI· Haotian Liu, Yingjian Chen, Xiaohang Xu, Lang Huang, Yusuke Iwasawa, Yutaka Matsuo, Irene Li·· 6 小时前
DDRG：通过推理图对齐实现 LLM 推理的细粒度纠错
Beyond Answer Voting: Fine-Grained Correction of LLM Reasoning through Graph Alignment across Sampled Traces
AI 导读
DDRG 框架通过构建基于来源的声明图并对齐采样推理轨迹，将局部冲突交给答案盲验证器，实现选择性纠错。在五个基准上，原生零样本 DDRG 对 Qwen2.5-7B 和 Llama3.1-8B 的宏平均准确率分别比直接回答提升 8.65 和 15.83 个百分点，并超过 CoT、GoT、GoV 及 SC。该方法在不扩大初始候选轨迹库的前提下，将局部验证与选择性纠错相连接。
正文
Abstract:Large language models increasingly tackle tasks that require multi-step reasoning, where errors in intermediate claims can affect the final answer. Self-consistency (SC) improves reasoning by voting over sampled final answers, but its vote leaves intermediate disagreements unresolved. To address this problem, we introduce DDRG (Disagreement-Driven Verification Guided by Reasoning Graphs), a framework for selective correction from a frozen bank of reasoning traces. Our insight is that graph alignment can expose claim-level disagreements and provide correction evidence without expanding the sampled trace bank. DDRG builds source-grounded claim graphs and sends localized conflicts to an answer-blind verifier. A verifier-supported refutation that reaches the majority answer's supporting path triggers one focused repair; otherwise, DDRG returns the exact SC vote. Experimental results across five benchmarks show that native zero-shot DDRG improves macro-average accuracy over direct answering by 8.65 and 15.83 percentage points for Qwen2.5-7B and Llama3.1-8B. It also exceeds CoT, the evaluated GoT and GoV question-answering adaptations, and SC on this macro metric. DDRG links local verification to selective correction without enlarging the initial candidate bank.
| Comments: | 19 pages, 5 figures, 4 tables. Under review |
| Subjects: | Artificial Intelligence (cs.AI); Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.18606 [cs.AI] |
| (or arXiv:2610.18606v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.18606 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Haotian Liu [view email]
[v1]
Tue, 13 Oct 2026 15:58:02 UTC (421 KB)
来源：arXiv：cs.AI · arxiv.org