What type of study is this?

This is a Quantitative Study study.

October 22, 2025

Training-Free Hybrid Evidence Retrieval for Question Answering: Dynamic Fusion of Knowledge-Graph Triples and Dense Text Embeddings

OXOtávio Calaça XavierUniversidade Federal de Goiás ASAnderson da Silva SoaresUniversidade Federal de Goiás

Key Points

analyzed their findings and outcomes to make sense of the data they collected, providing an analysis of their research. They employed various methods and techniques to gather information on their topic of interest, interpreting trends within their data.
created their work through careful planning and meticulous research, developing a clearer understanding of the subject matter.
the implications of their findings highlight their relevance to ongoing discussions and further inquiries within the field, contributing to the greater body of knowledge.

Abstract

This work presents a sub-50ms, training-free retrieval pipeline that leverages a Neo4j knowledge graph and a ChromaDB vector index. Questions and passages are embedded with Sentence-BERT, and the retrieved entities seed a one-hop Cypher expansion in the knowledge graph. A transparent fusion based on Dice-Sørensen overlap ranks both passages and triples. On the WebQSP and CQA-12k benchmarks, this hybrid method achieves superior Recall@10, MRR, and nDCG@10 compared to BM25, graph-only, and vectoronly baselines. Requiring no learned parameters and running on commodity hardware, it offers a practical alternative to heavyweight neural re-rankers and a robust evidence layer for retrieval-augmented generation (RAG).

KI fragen

Bookmark

View Full Paper