3 papers
cs.SE2026
ABTest: Behavior-Driven Testing for AI Coding Agents
Wuyang Dai, Moses Openja, Hung Viet Pham +3
AI coding agents are increasingly integrated into real-world software development workflows, yet their robustness under diverse and adversarial scenarios remains poorly understood.…
cs.SE2026
Tracing Stereotypes in Pre-trained Transformers: From Biased Neurons to Fairer Models
Gianmario Voria, Moses Openja, Foutse Khomh +2
The advent of transformer-based language models has reshaped how AI systems process and generate text. In software engineering (SE), these models now support diverse activities, ac…
cs.LG2025
FairFLRep: Fairness aware fault localization and repair of Deep Neural Networks
Moses Openja, Paolo Arcaini, Foutse Khomh +1
Deep neural networks (DNNs) are being utilized in various aspects of our daily lives, including high-stakes decision-making applications that impact individuals. However, these sys…