# TopClustRAG at SIGIR 2025 LiveRAG Challenge

Source: [TopClustRAG at SIGIR 2025 LiveRAG Challenge](<https://www.sota2.com/research/paper/68fa797f1e209131cea7dd1d>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T04:58:48.249Z

Authors: Juli Bakagianni, John Pavlopoulos, Aristidis Likas

Published: 2025-06-18T08:24:27.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2506.15246>)

[PDF](<https://arxiv.org/pdf/2506.15246.pdf>)
