TrustworthyRAG

Trustworthy RAG Un Agente de Evaluación para Detectar Desinformación y Envenenamiento del Conocimiento en Sistemas de Generación Aumentada por Recuperación. Visión general Este proyecto implementa un Trustworthy RAG Framework con un Agente de Evaluación integrado que evalúa la fiabilidad de las...

RAGSieve

RAGSieve Reference implementation for “RAGSieve: Self-Referenced Local Contrast for Knowledge-Poison Detection in Retrieval-Augmented Generation.” RAGSieve detects knowledge-poisoning documents at two control points in a retrieval-augmented generation RAG system. RAGSieve-Query RSQ is an online...

One Shot Dominance: Knowledge Poisoning Attack on Retrieval-Augmented Generation Systems

Large Language Models LLMs enhanced with Retrieval-Augmented Generation RAG have shown improved performance in generating accurate responses. However, the dependence on external knowledge bases introduces potential security vulnerabilities, particularly when these knowledge bases are publicly...