Knowledge-Aware Diverse Reranking for Cross-Source Question Answering

2025/06/25 by Tong Zhou, Zhou, Tong · 1 citation
Computer Science · #Topic Modeling #Domain Adaptation and Few-Shot Learning

paper · pdf · doi:10.48550/arxiv.2506.20476

Abstract

This paper presents Team Marikarp's solution for the SIGIR 2025 LiveRAG competition. The competition's evaluation set, automatically generated by DataMorgana from internet corpora, encompassed a wide range of target topics, question types, question formulations, audience types, and knowledge organization methods. It offered a fair evaluation of retrieving question-relevant supporting documents from a 15M documents subset of the FineWeb corpus. Our proposed knowledge-aware diverse reranking RAG pipeline achieved first place in the competition.

Citations

• Generating Diverse Q&A Benchmarks for RAG Evaluation with DataMorgana
• The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale
• A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models
• Retrieval-Augmented Generation for Large Language Models: A Survey
• Text Embeddings by Weakly-Supervised Contrastive Pre-training

Cited by

• SIGIR 2025 -- LiveRAG Challenge Report

Related

• TopClustRAG at SIGIR 2025 LiveRAG Challenge
• Can we repurpose multiple-choice question-answering models to rerank retrieved documents?
• Generating Diverse Q&A Benchmarks for RAG Evaluation with DataMorgana
• A strong baseline for question relevancy ranking
• SciRerankBench: Benchmarking Rerankers Towards Scientific Retrieval-Augmented Generated LLMs