Pith. sign in

REVIEW 4 cited by

Formal Specifications from Natural Language

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 2206.01962 v2 pith:DDRJVLMI submitted 2022-06-04 cs.SE cs.LGcs.PL

classification cs.SEcs.LGcs.PL
keywords languageformalmodelsnaturalexpressionsfine-tunegeneralizationlogic
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We study the generalization abilities of language models when translating natural language into formal specifications with complex semantics. In particular, we fine-tune language models on three datasets consisting of English sentences and their corresponding formal representation: 1) regular expressions (regex), frequently used in programming and search; 2) First-order logic (FOL), commonly used in software verification and theorem proving; and 3) linear-time temporal logic (LTL), which forms the basis for industrial hardware specification languages. Our experiments show that, in these diverse domains, the language models maintain their generalization capabilities from pre-trained knowledge of natural language to generalize, e.g., to new variable names or operator descriptions. Additionally, they achieve competitive performance, and even outperform the state-of-the-art for translating into regular expressions, with the benefits of being easy to access, efficient to fine-tune, and without a particular need for domain-specific reasoning.

Discussion (0). Sign in to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 13 citations worldwide. Full citation record

  1. HybridProver: Augmenting Theorem Proving with LLM-Driven Proof Synthesis and Refinement

    cs.FL 2025-05 conditional novelty 7.0 of 10

    A dual-model framework that extracts proof sketches from whole-proof candidates and refines them with a tactic model and Sledgehammer, reaching 59.4 percent on miniF2F in Isabelle.

  2. Lost in Translation? Converting RegExes for Log Parsing into Dynatrace Pattern Language

    cs.SE 2025-06 conditional novelty 6.0 of 10

    Reptile converts 73.7% of real-world log-parsing RegExes into DPL with test-validated semantic equivalence, and its GPT-4 pattern optimization reaches an average F1-score of 0.91 and MCC of 0.92 across five high-level...

  3. Requirements Development and Formalization for Reliable Code Generation: A Multi-Agent Vision

    cs.SE 2025-08 unverdicted novelty 5.0 of 10

    The paper proposes ReDeFo, a multi-agent pipeline that uses formal specifications and verification to generate reliable code from natural language requirements.

  4. A Short Survey on Formalising Software Requirements using Large Language Models

    cs.SE 2025-06 unverdicted novelty 1.0 of 10

    A survey summarizing 35 papers on using LLMs to formalize software requirements, but it contains no new experimental results and its classification tables have errors.

Pith tools