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.
TopClustRAG at SIGIR 2025 LiveRAG Challenge
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
We present TopClustRAG, a retrieval-augmented generation (RAG) system developed for the LiveRAG Challenge, which evaluates end-to-end question answering over large-scale web corpora. Our system employs a hybrid retrieval strategy combining sparse and dense indices, followed by K-Means clustering to group semantically similar passages. Representative passages from each cluster are used to construct cluster-specific prompts for a large language model (LLM), generating intermediate answers that are filtered, reranked, and finally synthesized into a single, comprehensive response. This multi-stage pipeline enhances answer diversity, relevance, and faithfulness to retrieved evidence. Evaluated on the FineWeb Sample-10BT dataset, TopClustRAG ranked 2nd in faithfulness and 7th in correctness on the official leaderboard, demonstrating the effectiveness of clustering-based context filtering and prompt aggregation in large-scale RAG systems.
citation-role summary
other 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
other 1polarities
unclear 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.