VisRAG achieves 20-40% better end-to-end performance than text-based RAG by directly embedding and retrieving document images with VLMs.
Wikichat: Stopping the hallucination of large language model chatbots by few-shot grounding on wikipedia
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
Introduces NPAS and AV Filter using LLM attention weights to defend RAG against poisoning, reporting up to 20% accuracy gains while adaptive attacks reach 35% success.
CRAVE is a new framework that clusters retrieved text and image evidence into narratives and uses an LLM judge to produce explained fact-checking verdicts.
citing papers explorer
-
VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents
VisRAG achieves 20-40% better end-to-end performance than text-based RAG by directly embedding and retrieving document images with VLMs.
-
Through the Stealth Lens: Attention-Aware Defenses Against Poisoning in RAG
Introduces NPAS and AV Filter using LLM attention weights to defend RAG against poisoning, reporting up to 20% accuracy gains while adaptive attacks reach 35% success.
-
Fact-Checking with Contextual Narratives: Leveraging Retrieval-Augmented LLMs for Social Media Analysis
CRAVE is a new framework that clusters retrieved text and image evidence into narratives and uses an LLM judge to produce explained fact-checking verdicts.