# Bootstrapping Fuzzers for Compilers of Low-Resource Language Dialects Using Language Models

arXiv: https://arxiv.org/abs/2512.05887 · HTML: https://mlsanity.com/paper/2512.05887/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Code and instruction data synthesis, one of 13 directions in Synthetic data and self-improvement for LLMs.
- Builds on 23 of its 56 references that are in the map.
- First posted on arXiv 5 Dec 2025.

## Placed in

- Synthetic data and self-improvement for LLMs / [Code and instruction data synthesis](https://mlsanity.com/synth/code-and-instruction-data-synthesis/)

## Builds on (most cited first, 23 of 23)

- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models](https://mlsanity.com/paper/2109.05093/) (2021)
- [Grammar-Constrained Decoding for Structured NLP Tasks without Finetuning](https://mlsanity.com/paper/2305.13971/) (2023)
- [Synchromesh: Reliable code generation from pre-trained language models](https://mlsanity.com/paper/2201.11227/) (2022)
- [SynCode: LLM Generation with Grammar Augmentation](https://mlsanity.com/paper/2403.01632/) (2024)
- [Grammar-Aligned Decoding](https://mlsanity.com/paper/2405.21047/) (2024)
- [Flexible and Efficient Grammar-Constrained Decoding](https://mlsanity.com/paper/2502.05111/) (2025)
- [Learn&Fuzz: Machine Learning for Input Fuzzing](https://mlsanity.com/paper/1701.07232/) (2017)
- [Fast Controlled Generation from Language Models with Adaptive Weighted Rejection Sampling](https://mlsanity.com/paper/2504.05410/) (2025)
- [FairFuzz: Targeting Rare Branches to Rapidly Increase Greybox Fuzz Testing Coverage](https://mlsanity.com/paper/1709.07101/) (2017)
- [Compiling ONNX Neural Network Models Using MLIR](https://mlsanity.com/paper/2008.08272/) (2020)
- [Constrained Sampling for Language Models Should Be Easy: An MCMC Perspective](https://mlsanity.com/paper/2506.05754/) (2025)
- [Souper: A Synthesizing Superoptimizer](https://mlsanity.com/paper/1711.04422/) (2017)
- [CodePAD: Sequence-based Code Generation with Pushdown Automaton](https://mlsanity.com/paper/2211.00818/) (2022)
- [Neural Program Synthesis with a Differentiable Fixer](https://mlsanity.com/paper/2006.10924/) (2020)
- [HEIR: A Universal Compiler for Homomorphic Encryption](https://mlsanity.com/paper/2508.11095/) (2025)
- [Fuzzing MLIR Compilers with Custom Mutation Synthesis](https://mlsanity.com/paper/2404.16947/) (2024)
- [A MLIR Dialect for Quantum Assembly Languages](https://mlsanity.com/paper/2101.11365/) (2021)
- [Constrained Adaptive Rejection Sampling](https://mlsanity.com/paper/2510.01902/) (2025)
- [A Systematic Impact Study for Fuzzer-Found Compiler Bugs](https://mlsanity.com/paper/1902.09334/) (2019)
- [DESIL: Detecting Silent Bugs in MLIR Compiler Infrastructure](https://mlsanity.com/paper/2504.01379/) (2025)
- [DSP-MLIR: A MLIR Dialect for Digital Signal Processing](https://mlsanity.com/paper/2408.11205/) (2024)
- [Interleaved Learning and Exploration: A Self-Adaptive Fuzz Testing Framework for MLIR](https://mlsanity.com/paper/2510.07815/) (2025)

## Built on by (most cited first, 1 of 1)

- [Learning the Error Patterns of Language Models](https://mlsanity.com/paper/2605.28328/) (2026)

## Abstract (arXiv)

Modern extensible compiler frameworks-such as MLIR-enable rapid creation of domain-specific language dialects. This flexibility, however, makes correctness harder to ensure as the same extensibility that accelerates development also complicates maintaining the testing infrastructure. Extensible languages require automated test generation that is both dialect-agnostic (works across dialects without manual adaptation) and dialect-effective (targets dialect-specific features to find bugs). Existing approaches typically sacrifice one of these goals by either requiring manually constructed seed corpora for each dialect, or by failing to be effective. We present a dialect-agnostic and dialect-effective grammar-based and coverage-guided fuzzing approach for extensible compilers that combines two key insights from existing work: (i) the grammars of dialects, which already encode the structural and type constraints, can often be extracted automatically from the dialect specification; and (ii) these grammars can be used in combination with pre-trained large language models to automatically generate representative and diverse seed inputs from the full dialect space without requiring any manual input or training data. These seeds can then be used to bootstrap coverage-guided fuzzers. We built this approach into a tool, Germinator. When evaluated on six MLIR projects spanning 91 dialects, Germinator generated seeds improve line coverage by 10-120% over grammar-based baselines. We compare against grammar-based baselines because they are the only class of existing automatic seed generators that can be applied uniformly across MLIR's heterogeneous dialect ecosystem. Germinator discovers 88 previously unknown bugs (40 confirmed), including 23 in dialects with no prior automated test generators, demonstrating effective and controllable testing of low-resource dialects at scale.