AI Slop and Hallucinations in Vulnerability Assessment: A Survey on Reasoning Failures and Trustworthy Mitigation
A taxonomy of AI slop grounded in a structured literature review is formalized and a roadmap for securing emerging AI-driven triage systems is provided, shifting evaluation from linguistic fluency to mathematical verifiability.
Junchen Ding, Jialiang Dong, Yi Zhu et al.
· arXiv.org · 0 citations