Pith. sign in

REVIEW 7 cited by

Synchromesh: Reliable code generation from pre-trained language models

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 2201.11227 v1 pith:5RXPIEPG submitted 2022-01-26 cs.LG cs.PL

Synchromesh: Reliable code generation from pre-trained language models

classification cs.LG cs.PL
keywords languageprogramscodepre-trainedsynchromeshmodelsnaturalsemantic
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Large pre-trained language models have been used to generate code,providing a flexible interface for synthesizing programs from natural language specifications. However, they often violate syntactic and semantic rules of their output language, limiting their practical usability. In this paper, we propose Synchromesh: a framework for substantially improving the reliability of pre-trained models for code generation. Synchromesh comprises two components. First, it retrieves few-shot examples from a training bank using Target Similarity Tuning (TST), a novel method for semantic example selection. TST learns to recognize utterances that describe similar target programs despite differences in surface natural language features. Then, Synchromesh feeds the examples to a pre-trained language model and samples programs using Constrained Semantic Decoding (CSD): a general framework for constraining the output to a set of valid programs in the target language. CSD leverages constraints on partial outputs to sample complete correct programs, and needs neither re-training nor fine-tuning of the language model. We evaluate our methods by synthesizing code from natural language descriptions using GPT-3 and Codex in three real-world languages: SQL queries, Vega-Lite visualizations and SMCalFlow programs. These domains showcase rich constraints that CSD is able to enforce, including syntax, scope, typing rules, and contextual logic. We observe substantial complementary gains from CSD and TST in prediction accuracy and in effectively preventing run-time errors.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 7 Pith papers

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

  1. Agentic generation of verifiable rules for deterministic, self-expanding reaction classification

    cs.AI 2026-07 unverdicted novelty 7.0

    Multi-agent LLMs generate and verify 14,073 deterministic reaction rules from 665,901 patents, enabling 97.7% classification of unseen reactions with finer resolution than fixed proprietary systems.

  2. Agentic generation of verifiable rules for deterministic, self-expanding reaction classification

    cs.AI 2026-07 conditional novelty 7.0

    Multi-agent LLMs classify USPTO reactions and write verified SMIRKS rules, expanding a 68-class taxonomy to 14,073 and classifying 97.7% of held-out reactions with a hybrid fingerprint-plus-template system.

  3. Agentic generation of verifiable rules for deterministic, self-expanding reaction classification

    cs.AI 2026-07 conditional novelty 7.0

    Multi-agent LLMs classify USPTO reactions and write verified SMIRKS rules, expanding a reaction taxonomy from 68 to 14,073 classes and matching proprietary classifiers on held-out and out-of-distribution data.

  4. PEARL: Auditable Repair for Scientific Reasoning Graph Extraction

    cs.AI 2026-07 conditional novelty 6.0

    PEARL repairs raw LLM scientific reasoning graphs with evidence-grounded judge feedback, raising strict gate passes from 0/350 to 300/350 on the ARCHE benchmark.

  5. To Know is to Construct: Schema-Constrained Generation for Agent Memory

    cs.CL 2026-04 unverdicted novelty 6.0

    SCG-MEM reformulates agent memory access as schema-constrained generation within dynamic cognitive schemas, using assimilation and accommodation for updates plus an associative graph for reasoning, and outperforms ret...

  6. TreeCoder: Systematic Exploration and Optimisation of Decoding and Constraints for LLM Code Generation

    cs.LG 2025-11 unverdicted novelty 6.0

    TreeCoder improves LLM code generation accuracy by representing decoding as an optimizable tree search over programs with first-class constraints for syntax, style, and execution, outperforming baselines on MBPP and S...

  7. A Dual-Track Framework for Template-Constrained LaTeX Conversion

    cs.CL 2026-06 unverdicted novelty 4.0

    Dual-track system extracts LaTeX template constraints offline into a manifest and applies hybrid LLM-rule processing online to improve structural fidelity and compilation success over baselines.