Metraipolis › archive › dc_d36cf2b5de05

Provably Tractable NFA-Constrained Language Generation via HMMs — arXiv:2609.40185

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.40185
License (as archived)
CC0-1.0
Archived
2026-10-07T13:14:10.208Z
SHA-256 of the archived text
9d2f17c59403c133f4c1acf069d6cd4f98d6a096ba3e5b0360febebabb13eec6
Stable URL of this page
https://metraipolis.com/documento/dc_d36cf2b5de05

How to cite

Provably Tractable NFA-Constrained Language Generation via HMMs — arXiv:2609.40185 — arXiv (en), https://arxiv.org/abs/2609.40185 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d36cf2b5de05 (Metraipolis archive dc_d36cf2b5de05, sha256 9d2f17c59403c133f4c1acf069d6cd4f98d6a096ba3e5b0360febebabb13eec6)
BibTeX
@misc{dcd36cf2b5de05,
  title = {Provably Tractable NFA-Constrained Language Generation via HMMs — arXiv:2609.40185},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.40185},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d36cf2b5de05; sha256 9d2f17c59403c133f4c1acf069d6cd4f98d6a096ba3e5b0360febebabb13eec6},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.40185. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Constrained generation aims to sample from language models (LMs) conditioned on hard constraints. Existing constrained-generation techniques for nondeterministic finite automaton (NFA) constraints either distort the distribution or sacrifice efficiency. Theoretically, this task reduces to counting the length-$n$ sequences accepted by an NFA (#NFA), and the exact #NFA problem is #P-complete. Recent work has shown that #NFA admits a fully polynomial randomized approximation scheme (FPRAS). Inspired by this result, we propose NFA-LM, a polynomial-time engine for NFA-constrained generation with theoretical guarantees under mild assumptions. Experiments show that NFA-LM efficiently generates high-quality outputs with theoretically bounded approximation error.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL) ; Formal Languages and Automata Theory (cs.FL).
Pagina del lavoro: https://arxiv.org/abs/2609.40185 — 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 2026-10-07T12:44:51.901Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).