Knowledge-Aware Diverse Reranking for Cross-Source Question Answering

TL;DR

This paper introduces a knowledge-aware diverse reranking method for cross-source question answering, achieving top results in the SIGIR 2025 LiveRAG competition by effectively handling diverse and large-scale data.

Contribution

It proposes a novel reranking pipeline that incorporates knowledge-awareness and diversity to improve cross-source question answering performance.

Findings

Achieved first place in the SIGIR 2025 LiveRAG competition.

Effectively retrieved relevant documents from a 15 million document corpus.

Demonstrated the effectiveness of knowledge-aware reranking in diverse question answering scenarios.

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.