Abstract

Pre-trained Large Language Models (LLMs) are beginning to dominate the discourse around automatic code generation with natural language specifications. In contrast, the best-performing synthesizers in the domain of formal synthesis with precise logical specifications are still based on enumerative algorithms. In this paper, we evaluate the abilities of LLMs to solve formal synthesis benchmarks by carefully crafting a library of prompts for the domain. When one-shot synthesis fails, we propose a novel enumerative synthesis algorithm, which integrates calls to an LLM into a weighted probabilistic search. This allows the synthesizer to provide the LLM with information about the progress of the enumerator, and the LLM to provide the enumerator with syntactic guidance in an iterative loop. We evaluate our techniques on benchmarks from the Syntax-Guided Synthesis (SyGuS) competition. We find that GPT-3.5 as a stand-alone tool for formal synthesis is easily outperformed by state-of-the-art formal synthesis algorithms, but our approach integrating the LLM into an enumerative synthesis algorithm shows significant performance gains over both the LLM and the enumerative synthesizer alone and the winning SyGuS competition tool.

BibTeX

@inproceedings{DBLP:conf/cav/LiPP24,
  author       = {Yixuan Li and
                  Julian Parsert and
                  Elizabeth Polgreen},
  editor       = {Arie Gurfinkel and
                  Vijay Ganesh},
  title        = {Guiding Enumerative Program Synthesis with Large Language Models},
  booktitle    = {Computer Aided Verification - 36th International Conference, {CAV}
                  2024, Montreal, QC, Canada, July 24-27, 2024, Proceedings, Part {II}},
  series       = {Lecture Notes in Computer Science},
  volume       = {14682},
  pages        = {280--301},
  publisher    = {Springer},
  year         = {2024},
  url          = {https://doi.org/10.1007/978-3-031-65630-9\_15},
  doi          = {10.1007/978-3-031-65630-9\_15},
  timestamp    = {Thu, 22 Aug 2024 20:23:18 +0200},
  biburl       = {https://dblp.org/rec/conf/cav/LiPP24.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}