Pith. sign in

REVIEW 5 cited by

Grammar-Constrained Decoding for Structured NLP Tasks without Finetuning

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2305.13971 v6 pith:UBM5KOE5 submitted 2023-05-23 cs.CL cs.AIcs.LG

classification cs.CLcs.AIcs.LG
keywords outputtasksgenerationgrammar-constrainedstructuredcodedatadecoding
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Despite their impressive performance, large language models (LMs) still struggle with reliably generating complex output structures when not finetuned to follow the required output format exactly. To address this issue, grammar-constrained decoding (GCD) can be used to control the generation of LMs, guaranteeing that the output follows a given structure. Most existing GCD methods are, however, limited to specific tasks, such as parsing or code generation. In this work, we demonstrate that formal grammars can describe the output space for a much wider range of tasks and argue that GCD can serve as a unified framework for structured NLP tasks in general. For increased flexibility, we introduce input-dependent grammars, which allow the grammar to depend on the input and thus enable the generation of different output structures for different inputs. We then empirically demonstrate the power and flexibility of GCD-enhanced LMs on (1) information extraction, (2) entity disambiguation, and (3) constituency parsing. Our results indicate that grammar-constrained LMs substantially outperform unconstrained LMs or even beat task-specific finetuned models. Grammar constraints thus hold great promise for harnessing off-the-shelf LMs for a wide range of structured NLP tasks, especially where training data is scarce or finetuning is expensive. Code and data: https://github.com/epfl-dlab/GCD.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Continuous Diffusion Models Can Obey Formal Syntax

    cs.LG 2026-02 conditional novelty 7.0 of 10

    Training-free gradient guidance, based on the exact regex-acceptance probability under the decoder's unigram distribution, lets continuous diffusion language models satisfy regular-expression constraints.

  2. Agentic Re-Casting using Agentic Re-Simulations

    hep-ph 2026-07 conditional novelty 6.0 of 10

    An agentic AI system with a physicist in the loop re-casts an ATLAS ttZ measurement into a global top-quark SMEFT fit and recovers injected coloron Wilson coefficients in a repeatable benchmark.

  3. AI Native Games: A Survey and Roadmap

    cs.AI 2026-07 unverdicted novelty 6.0 of 10

    The paper proposes a counterfactual definition of AI-native games, screens 53 examples, introduces a G/N taxonomy, and outlines a research roadmap for the field.

  4. The Format Tax

    cs.CL 2026-04 conditional novelty 6.0 of 10

    Structured-output instructions alone impose a large accuracy tax on open-weight LLMs; decoupling freeform reasoning from formatting recovers most of it, while recent closed models largely avoid the tax.

  5. Precise Robot Command Understanding Using Grammar-Constrained Large Language Models

    cs.RO 2026-04 conditional novelty 4.0 of 10

    A fine-tuned LLM plus grammar canonicalizer and feedback loop yields higher valid robot-command rates on HuRIC than a fine-tuned LLM or grammar NLU alone.

Pith tools