Metraipolis › archive › dc_26503fdaad48
From Transformers to Weighted Automata: Towards the Verification of Large Language Models — arXiv:2610.04569
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.04569
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T05:32:09.101Z
- SHA-256 of the archived text
bcef95b6afa36532aea4448bbc2b48770237f02d4c70450d02b8a0398db7a2ae- Stable URL of this page
https://metraipolis.com/documento/dc_26503fdaad48
How to cite
From Transformers to Weighted Automata: Towards the Verification of Large Language Models — arXiv:2610.04569 — arXiv, https://arxiv.org/abs/2610.04569 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_26503fdaad48 (Metraipolis archive dc_26503fdaad48, sha256 bcef95b6afa36532aea4448bbc2b48770237f02d4c70450d02b8a0398db7a2ae)
BibTeX
@misc{dc26503fdaad48,
title = {From Transformers to Weighted Automata: Towards the Verification of Large Language Models — arXiv:2610.04569},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.04569},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_26503fdaad48; sha256 bcef95b6afa36532aea4448bbc2b48770237f02d4c70450d02b8a0398db7a2ae},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.04569. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large language models (LLMs) are increasingly deployed in safety-critical settings, yet their black-box nature makes it difficult to provide formal guaranties about their behavior. Existing verification approaches rely primarily on empirical probing and testing, leaving open the question of how to reason rigorously about general-purpose trans- former architectures. In this work, we establish a principled bridge between transformers and weighted automata, a classical model from formal language theory. This connection enables us to transfer verification tools from automata the- ory to the analysis of LLMs. Our contributions are twofold: First, we develop a formal correspondence between transformer architectures and weighted automata over reals, showing how distributional properties of LLMs can be captured within this framework. Second, we introduce an identity testing algorithm for weighted automata that provides a statis- tical method for distinguishing whether two stochastic models define the same distribution up to a tolerance threshold. This work provides the first formal bridge between modern neural se- quence models and classical automata theory, clarifying both the poten- tial and the computational challenges for rigorous LLM verification. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Formal Languages and Automata Theory (cs.FL) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.04569 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-06T05:27:05.971Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).