Metraipolis › archive › dc_edf2c91df367

Specification-Guided Generation for Large Language Models — arXiv:2610.41511

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.41511
License (as archived): CC0-1.0
Archived: 2026-11-03T07:11:33.181Z
SHA-256 of the archived text: bdf97d2b594f2cccad4fdc4d9fa82023c2848e8af87238ed6b138441fb678172
Stable URL of this page: https://metraipolis.com/documento/dc_edf2c91df367

How to cite

Specification-Guided Generation for Large Language Models — arXiv:2610.41511 — arXiv (en), https://arxiv.org/abs/2610.41511 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_edf2c91df367 (Metraipolis archive dc_edf2c91df367, sha256 bdf97d2b594f2cccad4fdc4d9fa82023c2848e8af87238ed6b138441fb678172)

BibTeX

@misc{dcedf2c91df367,
  title = {Specification-Guided Generation for Large Language Models — arXiv:2610.41511},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41511},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_edf2c91df367; sha256 bdf97d2b594f2cccad4fdc4d9fa82023c2848e8af87238ed6b138441fb678172},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41511. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language models (LLMs) can generate structured outputs, but existing constrained-decoding methods mainly enforce syntax and cannot directly enforce satisfaction of a formal specification. We introduce a neuro-symbolic, specification-guided decoding framework that combines LLM generation with symbolic reasoning. At each step, the framework refines the decoding grammar by filtering out values that cannot be extended to an output satisfying the specification. We present a forward-only variant that guarantees specification satisfaction by construction, and a backtracking variant that revises earlier feasible choices when their downstream consequences leave only values that the LLM itself judges unsuitable. The framework is model-agnostic, requires no retraining, and builds on existing grammar-constrained decoding mechanisms. Experiments on configuration and constraint-solving benchmarks show that the forward-only variant reliably produces specification-compliant outputs while reducing repeated LLM inference compared with rejection sampling and incurring modest symbolic-reasoning overhead. The backtracking variant further reduces cases in which the model is forced to select values that it has itself judged unsuitable, thereby substantially improving adherence to the LLM's stated interpretation of the prompt.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.41511 — 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 2026-11-03T07:09:31.775Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).