Graph of Verification: Structured Verification of LLM Reasoning with Directed Acyclic Graphs
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (36) · 30665-30672
DOI: 10.1609/aaai.v40i36.40322 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Jiwei Fang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref).
Abstract (Originalsprache)
Verifying the complex and multi-step reasoning of Large Language Models (LLMs) is a critical challenge, as holistic methods often overlook localized flaws. Step-by-step validation is a promising alternative, yet existing methods are often rigid. They struggle to adapt to diverse reasoning structures, from formal proofs to informal natural language narratives. To address this adaptability gap, we propose the Graph of Verification (GoV), a novel framework for adaptable and multi-granular verification. GoV's core innovation is its flexible node block architecture. This mechanism allows GoV to adaptively adjust its verification granularity—from atomic steps for formal tasks to entire paragraphs for natural language—to match the native structure of the reasoning process. This flexibility allows GoV to resolve the fundamental trade-off between verification precision and robustness. Experiments on both well-structured and loosely-structured benchmarks demonstrate GoV's versatility. The results show that GoV's adaptive approach significantly outperforms both holistic baselines and other state-of-the-art decomposition-based methods, establishing a new standard for training-free reasoning verification.
Zitieren
APA
Fang, J., Zhang, B., Wang, C., Wan, J., & Xu, Z. (2026). Graph of Verification: Structured Verification of LLM Reasoning with Directed Acyclic Graphs. Proceedings of the AAAI Conference on Artificial Intelligence, 40(36), 30665-30672. https://doi.org/10.1609/aaai.v40i36.40322
Vancouver
Fang J, Zhang B, Wang C, Wan J, Xu Z. Graph of Verification: Structured Verification of LLM Reasoning with Directed Acyclic Graphs. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(36):30665-30672. doi:10.1609/aaai.v40i36.40322
BibTeX
@article{Fang2026,
author = {Fang, Jiwei and Zhang, Bin and Wang, Changwei and Wan, Jin and Xu, Zhiwei},
title = {Graph of Verification: Structured Verification of LLM Reasoning with Directed Acyclic Graphs},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {36},
pages = {30665--30672},
doi = {10.1609/aaai.v40i36.40322}
}
EUVIMED