RAGStress Benchmark
Explore score history ↗Retrieval-Augmented Generation (RAG) is typically evaluated under the implicit assumption that the underlying knowledge base (KB) is clean, leaving the behaviour of RAG systems under realistic KB degradation poorly characterised.
- Released
- 2026-10-03
- Evaluates
- Factuality, General AI, Information retrieval, Language & Knowledge, cs.AI
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- rule-auto-admitted
RAGStress paper
No reported scores are on record for this benchmark yet.