Search Results for author:
Found 12 papers, 2 papers with code
Was it Slander? Towards Exact Inversion of Generative Language Models
Training large language models (LLMs) requires a substantial investment of time and money.
Automated Repair of AI Code with Large Language Models and Formal Verification
Then, we verify the memory safety of the mutated neural network implementations with ESBMC, a state-of-the-art software verifier.
NeuroCodeBench: a plain C neural network benchmark for software verification
Safety-critical systems with neural network components require strong guarantees.
LF-checker: Machine Learning Acceleration of Bounded Model Checking for Concurrency Verification (Competition Contribution)
We describe and evaluate LF-checker, a metaverifier tool based on machine learning.
Towards Global Neural Network Abstractions with Locally-Exact Reconstruction
Unfortunately, existing abstraction techniques are slack, which limits their applicability to small local regions of the input domain.
Montague semantics and modifier consistency measurement in neural language models
At the same time, the need for interpretability has elicited questions on their intrinsic properties and capabilities.
CEG4N: Counter-Example Guided Neural Network Quantization Refinement
Existing quantization techniques tend to degrade the network accuracy.
Systematicity, Compositionality and Transitivity of Deep NLP Models: a Metamorphic Testing Perspective
Metamorphic testing has recently been used to check the safety of neural NLP models.
QNNVerifier: A Tool for Verifying Neural Networks using SMT-Based Model Checking
QNNVerifier is the first open-source tool for verifying implementations of neural networks that takes into account the finite word-length (i. e. quantization) of their operands.
Verifying Quantized Neural Networks using SMT-Based Model Checking
Furthermore, for small- to medium-sized ANN, our approach completes most of its verification runs in minutes.
Streaming Bayesian Inference for Crowdsourced Classification
Third, SBIC has provable asymptotic guarantees both in the online and offline settings.
Efficiency of active learning for the allocation of workers on crowdsourced classification tasks
Crowdsourcing has been successfully employed in the past as an effective and cheap way to execute classification tasks and has therefore attracted the attention of the research community.
