no code implementations • 6 Mar 2024 • Yixuan Li, Julian Parsert, Elizabeth Polgreen
In this paper, we evaluate the abilities of LLMs to solve formal synthesis benchmarks by carefully crafting a library of prompts for the domain.
no code implementations • 6 Oct 2023 • Alexander Brauckmann, Elizabeth Polgreen, Tobias Grosser, Michael F. P. O'Boyle
MLIR is an emerging compiler infrastructure for modern hardware, but existing programs cannot take advantage of MLIR's high-performance compilation if they are described in lower-level general purpose languages.
no code implementations • 13 Jul 2023 • Julian Parsert, Elizabeth Polgreen
To address this, we present a method for automatically generating training data for SyGuS based on anti-unification of existing first-order satisfiability problems, which we use to train our MCTS policy.
no code implementations • 28 Jul 2021 • Elizabeth Polgreen, Andrew Reynolds, Sanjit A. Seshia
As a necessary component of this framework, we also formalize the problem of satisfiability modulo theories and oracles, and present an algorithm for solving this problem.
no code implementations • 13 Jul 2020 • Nicolas Chan, Elizabeth Polgreen, Sanjit A. Seshia
The performance of a syntax-guided synthesis algorithm is highly dependent on the provision of a good syntactic template, or grammar.
no code implementations • 25 Jan 2020 • Elizabeth Polgreen, Ralph Abboud, Daniel Kroening
Program synthesis is the generation of a program from a specification.
no code implementations • 5 Jul 2017 • Elizabeth Polgreen, Viraj Wijesuriya, Sofie Haesaert, Alessandro Abate
We present a new method for statistical verification of quantitative properties over a partially unknown system with actions, utilising a parameterised model (in this work, a parametric Markov decision process) and data collected from experiments performed on the underlying system.