APD framework disentangles adversarial prompts via mutual information decomposition, spectral graph analysis, and a trained classifier to cut harmful LLM outputs by over 85%.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
CogniVerse is a proposed MMRAG framework that combines cognitive reflection for retrieval filtering, Riemannian manifold alignment plus spectral graphs for retrieval, and optimal transport loss for generation, claiming better accuracy, coherence, and lower latency than prior systems.
citing papers explorer
-
Disentangling Adversarial Prompts: A Semantic-Graph Defense for Robust LLM Security
APD framework disentangles adversarial prompts via mutual information decomposition, spectral graph analysis, and a trained classifier to cut harmful LLM outputs by over 85%.
-
CogniVerse: Revolutionizing Multi-Modal Retrieval-Augmented Generation with Cognitive Reflection and Geometric Reasoning
CogniVerse is a proposed MMRAG framework that combines cognitive reflection for retrieval filtering, Riemannian manifold alignment plus spectral graphs for retrieval, and optimal transport loss for generation, claiming better accuracy, coherence, and lower latency than prior systems.