Synergizing LLMs and Formal Methods for Neural-Symbolic Reasoning
Communications of the ACM · 10.11.2026
DOI: 10.1145/3812808 ↗Kurz gefasst
Fachartikel in der Zeitschrift Communications of the ACM, online erschienen am 10.11.2026. Verfasst von Jin-Song Dong und 6 weiteren Autor:innen. Die Arbeit nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Research Foundation Singapore, Ministry of Education - Singapore.
Abstract (Originalsprache)
Large language models (LLMs) have demonstrated remarkable capabilities in natural language understanding, generation, and reasoning, but their outputs remain probabilistic and error-prone. Formal methods (FM), by contrast, provide mathematically rigorous reasoning, but suffer from limited accessibility. This article explores a neural-symbolic paradigm that unifies these complementary strengths and presents case studies that illustrate how LLMs can lower the entry barrier to formal methods while the latter provide reliability, interpretability, and guarantees absent in purely neural AI models. We argue that synergizing LLMs with formal methods is a promising direction for building AI systems that are not only powerful but also trustworthy by construction.
Förderung
- National Research Foundation Singapore
- Ministry of Education - Singapore
Zitieren
APA
Dong, J., Cai, Y., Hou, Z., Sun, J., Wang, H., Zhang, Y., & Zuo, X. (2026). Synergizing LLMs and Formal Methods for Neural-Symbolic Reasoning. Communications of the ACM. https://doi.org/10.1145/3812808
Vancouver
Dong J, Cai Y, Hou Z, Sun J, Wang H, Zhang Y, et al. Synergizing LLMs and Formal Methods for Neural-Symbolic Reasoning. Communications of the ACM. 2026. doi:10.1145/3812808
BibTeX
@article{Dong2026,
author = {Dong, Jin-Song and Cai, Yufan and Hou, Zhe and Sun, Jing and Wang, Hongshu and Zhang, Yedi and Zuo, Xinyue},
title = {Synergizing LLMs and Formal Methods for Neural-Symbolic Reasoning},
journal = {Communications of the ACM},
year = {2026},
doi = {10.1145/3812808}
}
EUVIMED