In the SIGIR 2025 LiveRAG Challenge, all 25 active RAG teams beat the no-RAG baseline on LLM-judged correctness, and LLM scores correlated with human scores at r=0.88.
Retrieval-augmented generation for knowledge- intensive NLP tasks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
SIGIR 2025 -- LiveRAG Challenge Report
In the SIGIR 2025 LiveRAG Challenge, all 25 active RAG teams beat the no-RAG baseline on LLM-judged correctness, and LLM scores correlated with human scores at r=0.88.