相关论文: VeriStruct: AI-assisted Automated Verification of …

Fully automated verification of large-scale software and hardware systems is arguably the holy grail of formal methods. Large language models (LLMs) have recently demonstrated their potential for enhancing the degree of automation in formal…

Recent verification tools aim to make formal verification more accessible to software engineers by automating most of the verification process. However, annotating conventional programs with the formal specification and verification…

Large language models (LLMs) have demonstrated impressive capabilities in generating software code for high-level programming languages such as Python and C++. However, their application to hardware description languages, such as Verilog,…

Rust is a programming language that combines memory safety and low-level control, providing C-like performance while guaranteeing the absence of undefined behaviors by default. Rust's growing popularity has prompted research on safe and…

The Verified Software Toolchain (VST) is a system for proving correctness of C programs using separation logic. By connecting to the verified compiler CompCert, it produces the strongest possible guarantees of correctness for real C code…

Large Language Models (LLMs) are computational models capable of performing complex natural language processing tasks. Leveraging these capabilities, LLMs hold the potential to transform the entire hardware design stack, with predictions…

Noisy data, non-convex objectives, model misspecification, and numerical instability can all cause undesired behaviors in machine learning systems. As a result, detecting actual implementation errors can be extremely difficult. We…

Reliable verification of proofs remains a bottleneck for training and evaluating AI systems on hard mathematical reasoning. Fully formal proofs, in languages like Lean, are easy to verify because they are unambiguous and modular. Most…

Distributed systems adopt weak consistency to ensure high availability and low latency, but state convergence is hard to guarantee due to conflicts. Experts carefully design replicated data types (RDTs) that resemble sequential data types…

VeriFast is one of the leading tools for semi-automated modular formal program verification. A central feature of VeriFast is its support for higher-order ghost code, which enables its support for expressively specifying fine-grained…

The proliferation of misinformation poses a significant threat to society, exacerbated by the capabilities of generative AI. This demo paper introduces Veracity, an open-source AI system designed to empower individuals to combat…

We present a methodology for formal verification of arithmetic RTL designs that combines sequential logic equivalence checking with interactive theorem proving. An intermediate model of a Verilog module is hand-coded in Restricted…

Certified program synthesis (aka vericoding) is the process of automatically generating a program, its formal specification, and a machine-checkable proof of their alignment from a natural-language description. Two challenges make…

Metrics like FactScore and VeriScore that evaluate long-form factuality operate by decomposing an input response into atomic claims and then individually verifying each claim. While effective and interpretable, these methods incur numerous…

Large Language Models (LLMs) have demonstrated remarkable potential in debugging for various programming languages. However, the application of LLMs to Verilog debugging remains insufficiently explored. Here, we present VeriDebug, an…

Formal verification provides a rigorous and systematic approach to ensure the correctness and reliability of software systems. Yet, constructing specifications for the full proof relies on domain expertise and non-trivial manpower. In view…

Structured Outputs from current LLMs exhibit sporadic errors, hindering enterprise AI deployment. We present CONSTRUCT, a real-time uncertainty estimator that scores the trustworthiness of LLM Structured Outputs. Lower-scoring outputs are…

Vericoding refers to the generation of formally verified code from rigorous specifications. Recent AI models show promise in vericoding, but a unified methodology for cross-paradigm evaluation is lacking. Existing benchmarks test only…

The main issue with most evaluation schemes today is their "static" nature: the same problems are reused repeatedly, allowing for memorization, format exploitation, and eventual saturation. To measure genuine AI progress, we need evaluation…

TextGrad is a novel approach to text-based automatic differentiation that enables composite AI systems to perform optimization without explicit numerical equations. However, it currently lacks self-verification mechanisms that ensure…