arXiv Computation and Language October 1, 2026 By Jialiang Sun, Kuldeep Meel

Provably Tractable NFA-Constrained Language Generation via HMMs

Read the original on arXiv Computation and Language →

The paper introduces NFA-LM, a polynomial‑time method for generating language model outputs that satisfy nondeterministic finite automaton (NFA) constraints. It leverages recent results that the #NFA counting problem admits a fully polynomial randomized approximation scheme, providing theoretical guarantees under mild assumptions. Experiments demonstrate that NFA‑LM produces high‑quality outputs efficiently while keeping approximation error bounded.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

llms

arXiv Machine Learning

Jul 9

Constrained Decoding for Diffusion Language Models via Efficient Inference over Finite Automata

arXiv:2607. 07026v1 Announce Type: new Abstract: Constrained decoding is essential for serving LLMs, ensuring that generated outputs follow specific structures such as JSON schema-formatted function calls.

By Meihua Dang, Stefano Ermon

llms agents diffusion data-engineering

Hugging Face Trending Papers

Jul 8

Constrained Decoding for Diffusion Language Models via Efficient Inference over Finite Automata

Constrained decoding is essential for serving LLMs, ensuring that generated outputs follow specific structures such as JSON schema-formatted function calls. Existing systems are designed for autoregressive models and assume left-to-right generation, masking out invalid next tokens at each step.

llms agents diffusion data-engineering

arXiv AI

Jul 24

Tractable Hierarchical Control of Autoregressive Language Models

arXiv:2607. 20483v1 Announce Type: new Abstract: Constraining the generation of autoregressive large language models (LLMs) is an important component of integrating language models into formal systems.

By Max Scribner, Antonio Vergari, Vaishak Belle

llms data-engineering

arXiv Computation and Language

3d ago

Making Grid Beam Search Less Greedy

arXiv:2609.39368v1 Announce Type: new Abstract: A common formalism for constraining the output of autoregressive text generation models involves lexical constraints, words or phrases which are requir...

By Sean Papay, Roman Klinger

safety

arXiv AI

Jun 4

Constrained Adaptive Rejection Sampling

arXiv:2510. 01902v2 Announce Type: replace Abstract: Language Models (LMs) are increasingly used in applications where generated outputs must satisfy strict semantic or syntactic constraints.

By Pawe{\l} Parys, Sairam Vaidya, Taylor Berg-Kirkpatrick, Loris D'Antoni

llms efficiency

arXiv Computation and Language

Aug 25

Lookahead-then-Verify: Reliable Constrained Decoding for Diffusion LLMs under Context-Free Grammars

arXiv:2602.00612v3 Announce Type: replace Abstract: Diffusion Large Language Models (dLLMs) have demonstrated promising generative capabilities and are increasingly used to produce formal languages d...

By Yitong Zhang, Yongmin Li, Yuetong Liu, Jia Li, Xiaoran Jia, Zherui Li, Ge Li

llms diffusion benchmarks

One email a morning, machine-written

Related stories

Constrained Decoding for Diffusion Language Models via Efficient Inference over Finite Automata

Constrained Decoding for Diffusion Language Models via Efficient Inference over Finite Automata

Tractable Hierarchical Control of Autoregressive Language Models

Making Grid Beam Search Less Greedy

Constrained Adaptive Rejection Sampling

Lookahead-then-Verify: Reliable Constrained Decoding for Diffusion LLMs under Context-Free Grammars