Author

David Mohaisen

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#software testing Preprint Oct 2026

Learning from Failures: A Failure-Driven Prompt Refinement for LLM-Based Vulnerability Analysis

This work proposes Failure-Driven Prompt Refinement (FDPR), a methodology that analyzes recurring model failures to guide evidence-based prompt refinement, and shows that failure-driven refinement improves the reliability of LLM-based vulnerability analysis while yielding reusable prompt design principles.

Mandana Ghadamian, David Mohaisen · 0 citations