TopClustRAG at SIGIR 2025 LiveRAG Challenge

Juli Bakagianni, John Pavlopoulos, Aristidis Likas
6/18/2025
cs.CL

No confident code implementation found for this paper. 1 possible match can be shown below.

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.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 1 weaker match is hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

CRAG - Comprehensive RAG Benchmark

85% match1 repo3112024

Cluster-based Adaptive Retrieval: Dynamic Context Selection for RAG Applications

84% match1 repo12025

Evaluating Hybrid Retrieval Augmented Generation using Dynamic Test Sets: LiveRAG Challenge

83% match2025

SIGIR 2025 -- LiveRAG Challenge Report

83% match2025

W-RAG: Weakly Supervised Dense Retrieval in RAG for Open-domain Question Answering

83% match1 repo162024

KeyKnowledgeRAG (K^2RAG): An Enhanced RAG method for improved LLM question-answering capabilities

83% match2025

Cite this paper

@article{bakagianni2025topclustrag,
  title  = {TopClustRAG at SIGIR 2025 LiveRAG Challenge},
  author = {Juli Bakagianni and John Pavlopoulos and Aristidis Likas},
  year   = {2025},
  eprint = {2506.15246},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2506.15246v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2506.15246.svg)](https://codeofpaper.com/paper/2506.15246)

Discussion