TopClustRAG at SIGIR 2025 LiveRAG Challenge
On the map: Retrieval-augmented generation → RAG robustness and adaptive retrieval
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation. Builds on 3 of its 10 references that are in the map. First posted on arXiv 18 Jun 2025.
Builds on
3 of 10 references.
References · 3
- 2022Text Embeddings by Weakly-Supervised Contrastive Pre-trainingcited by 1,253
- 2024The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scalecited by 1,160
- 2024Jasper and Stella: distillation of SOTA embedding modelscited by 112
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025PreQRAG -- Classify and Rewrite for Enhanced RAG
- 2025NodeRAG: Structuring Graph-based RAG with Heterogeneous Nodes
- 2025mmRAG: A Modular Benchmark for Retrieval-Augmented Generation over Text, Tables, and Knowledge Graphs
- 2025Evaluating Hybrid Retrieval Augmented Generation using Dynamic Test Sets: LiveRAG Challenge
- 2025Cooperative Retrieval-Augmented Generation for Question Answering: Mutual Information Exchange and Ranking by Contrasting Layers
- 2025SAGE: A Framework of Precise Retrieval for RAG
- 2025ArchRAG: Attributed Community-based Hierarchical Retrieval-Augmented Generation
- 2026A Matryoshka Hierarchical RAG for Efficient Multi-Hop Question Answering