EcoSafeRAG filters poisoned or injected documents from RAG inputs by sentence-level splitting plus bait-guided DBSCAN clustering of context vectors, before the language model generates an answer.
This measures both the presence of noise points and the number of distinct non-noise clusters, ensuring the data exhibits natural variation across multiple dimensions
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
EcoSafeRAG: Efficient Security through Context Analysis in Retrieval-Augmented Generation
EcoSafeRAG filters poisoned or injected documents from RAG inputs by sentence-level splitting plus bait-guided DBSCAN clustering of context vectors, before the language model generates an answer.