arXiv Machine Learning June 10, 2026 By Willem Meijer, Kristian Sandahl, D\'aniel Varr\'o

Data-aware Static Analysis: Improving Detection of Semantic Faults in Machine Learning Code Using Data Characteristics

Read the original on arXiv Machine Learning →

arXiv:2606. 09957v1 Announce Type: cross Abstract: Semantic faults specific to the use of machine learning models are a common problem for machine learning developers, causing suboptimal predictions, high computational cost, or incorrect outputs.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv AI

Jul 1

SpecDetect4ML: Detecting Non-Local ML Code Smells with Code Property Graphs

arXiv:2509. 20491v3 Announce Type: replace-cross Abstract: Machine Learning (ML) pipelines encode quality-relevant decisions across data preparation, training, evaluation, and configuration code.

By Brahim Mahmoudi, Naouel Moha, Quentin Sti\'evenart, Florent Avellaneda

benchmarks

arXiv AI

6d ago

Program Semantic Inequivalence Game with Large Language Models

arXiv:2505. 03818v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) can achieve strong performance on everyday coding tasks, but they can fail on complex tasks that require non-trivial reasoning about program semantics.

By Antonio Valerio Miceli-Barone, Vaishak Belle, Ali Payani

llms agents fine-tuning benchmarks

arXiv Machine Learning

Jul 15

Deep4ge: DNN Training Trajectories for Fault Detection and Diagnosis

arXiv:2607. 12868v1 Announce Type: cross Abstract: Deep learning systems often fail due to subtle implementation faults that alter training behavior.

By Sigma Jahan

benchmarks

arXiv AI

Jun 30

Faults in Our Formal Benchmarking: Dataset Defects and Evaluation Failures in Lean Theorem Proving

arXiv:2606. 29493v1 Announce Type: new Abstract: Benchmarks for LLM-assisted theorem proving in Lean are often treated as intrinsically reliable because every solved instance comes with a machine-checked proof.

By Pawan Sasanka Ammanamanchi, Siddharth Bhat, Stella Biderman

llms benchmarks safety

arXiv Machine Learning

Jun 18

OpenAnt: LLM-Powered Vulnerability Discovery Through Code Decomposition, Adversarial Verification, and Dynamic Testing

arXiv:2606. 19149v1 Announce Type: cross Abstract: Automated vulnerability discovery in large codebases remains challenging: traditional static analysis produces high false-positive rates, while dynamic approaches such as fuzzing require substantial infrastructure and often target narrow classes of bugs.

By Nahum Korda, Gadi Evron

llms safety

arXiv Machine Learning

Jun 11

DeMix: Debugging Training Data with Mixed Data Error Types by Investigating Influence Vectors

arXiv:2606. 11616v1 Announce Type: new Abstract: High-quality training data is essential for the success of machine learning models.

By Jiale Deng, Yanyan Shen, Xiaogang Shi, Chai Junjun

llms benchmarks safety

Related stories

SpecDetect4ML: Detecting Non-Local ML Code Smells with Code Property Graphs

Program Semantic Inequivalence Game with Large Language Models

Deep4ge: DNN Training Trajectories for Fault Detection and Diagnosis

Faults in Our Formal Benchmarking: Dataset Defects and Evaluation Failures in Lean Theorem Proving

OpenAnt: LLM-Powered Vulnerability Discovery Through Code Decomposition, Adversarial Verification, and Dynamic Testing

DeMix: Debugging Training Data with Mixed Data Error Types by Investigating Influence Vectors