A hybrid extract-then-summarize framework that first identifies salient sentences using a supervised extractive model and then generates an abstractive summary through LLM prompting is proposed, which improves efficiency by focusing the generative process on informative content while reducing the processing cost typica...
Azzedine Aftiss, Salima Lamsiyah, Christoph Schommer et al.· IEEE Access· 0 citations
RECTIFY, an interactive Streamlit workbench that turns evaluated RAG cases into auditable repair workflows, is presented, showing that pre-filtering reduces unnecessary repair candidates and that slicelevel routing yields more targeted repair cards than broad family-level diagnosis.
Keerthana Murugaraj, Salima Lamsiyah, Martin Theobald· 0 citations
NotAI.AI combines sentence-level conditional probability curvature, a neural detector score, and interpretable stylometric and readability features in an XGBoost meta-classifier and explains predictions with TreeSHAP feature contributions and can turn the resulting evidence into a concise natural-language explanation.
Oleksandr Marchenko Breneur, Adelaide Danilov, A. Nourbakhsh et al.· arXiv.org· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.