Modelpedia
Work in progress
About
Findings
Models
Concepts
Methods
Datasets
Sources
Light
Dark
Sufficient Context: A New Lens on Retrieval Augmented Generation Systems
2025-01-22
· ICLR 2025 Poster ·
anchor
Findings
IC-174
RAG reduces model abstention and LLMs hallucinate rather than abstain when the retrieved context is insufficient to answer the query
IC-175
Context-sufficiency performance is scale-dependent: larger LLMs achieve high accuracy with sufficient context but still answer correctly 35-62% of the time without it, while smaller models hallucinate or abstain even with sufficient context