LIT-RAGBench is a new benchmark with 114 questions evaluating RAG generator LLMs on integration, reasoning, logic, tables, and abstention, finding no model exceeds 90% overall accuracy.
FRAMES (Krishna et al., 2025) provides an integrated, end-to-end evaluation of bothR and G capabilities across three aspects—factuality, re- trieval, and reasoning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
LIT-RAGBench: Benchmarking Generator Capabilities of Large Language Models in Retrieval-Augmented Generation
LIT-RAGBench is a new benchmark with 114 questions evaluating RAG generator LLMs on integration, reasoning, logic, tables, and abstention, finding no model exceeds 90% overall accuracy.