Baldur: Whole-proof generation and repair with large language models
Formally verifying software is a highly desirable but labor-intensive task. Recent work has
developed methods to automate formal verification using proof assistants, such as Coq and …
developed methods to automate formal verification using proof assistants, such as Coq and …
Passport: Improving automated formal verification using identifiers
Formally verifying system properties is one of the most effective ways of improving system
quality, but its high manual effort requirements often render it prohibitively expensive. Tools …
quality, but its high manual effort requirements often render it prohibitively expensive. Tools …
Can Transformers Learn to Solve Problems Recursively?
SD Zhang, C Tigges, S Biderman, M Raginsky… - ar** software engineers write
programs and even formally verify them. While semantic information plays a crucial part in …
programs and even formally verify them. While semantic information plays a crucial part in …
LLMSTEP: LLM proofstep suggestions in Lean
We present LLMSTEP, a tool for integrating a language model into the Lean proof assistant.
LLMSTEP is a Lean 4 tactic that sends a user's proof state to a server hosting a language …
LLMSTEP is a Lean 4 tactic that sends a user's proof state to a server hosting a language …
Transformer-based models are not yet perfect at learning to emulate structural recursion
This paper investigates the ability of transformer-based models to learn structural recursion
from examples. Recursion is a universal concept in both natural and formal languages …
from examples. Recursion is a universal concept in both natural and formal languages …
Seldonian toolkit: Building software with safe and fair machine learning
We present the Seldonian Toolkit, which enables software engineers to integrate provably
safe and fair machine learning algorithms into their systems. Software systems that use data …
safe and fair machine learning algorithms into their systems. Software systems that use data …
Better automatic program repair by using bug reports and tests together
Automated program repair is already deployed in industry, but concerns remain about repair
quality. Recent research has shown that one of the main reasons repair tools produce …
quality. Recent research has shown that one of the main reasons repair tools produce …
CoqPilot, a plugin for LLM-based generation of proofs
A Kozyrev, G Solovev, N Khramov… - Proceedings of the 39th …, 2024 - dl.acm.org
We present CoqPilot, a VS Code extension designed to help automate writing of Coq proofs.
The plugin collects the parts of proofs marked with the admit tactic in a Coq file, ie, proof …
The plugin collects the parts of proofs marked with the admit tactic in a Coq file, ie, proof …