DBScholar

Back to papers

RAGPerf: An End-to-End Benchmarking Framework for Retrieval-Augmented Generation Systems

Summary: RAGPerf is an end-to-end, modular benchmark that isolates embedding, indexing, retrieval, reranking, and generation in configurable RAG pipelines. It combines realistic multimodal/update workloads with vector DB/LLM support and automated systems-quality metrics at negligible overhead. (summarized by gpt-5.6-luna on Aug 28 2026)

Paper ID
h6e1e6cbad3a839e4
Venue
VLDB
Year
2026
Pagerank
4.9793485e-05
Overall Rank
10,890 | 26.79%
DOI
10.14778/3836663.3836718

Incoming Non-self Citations Over Time

No non-self incoming citations found for this paper in this database.

Authors

BibTeX Citation

@article{li_vldb26,
        title = {{RAGPerf: An End-to-End Benchmarking Framework for Retrieval-Augmented Generation Systems}},
        author = {Li, Shaobo and Zhou, Yirui and Xu, Yuan and Chen, Kevin and Waddington, Daniel and Sundararaman, Swaminathan and Franke, Hubertus and Huang, Jian},
        journal = {PVLDB},
        series = {{VLDB} '26},
        volume = {19},
        number = {11},
        pages = {3689--3703},
        doi = {10.14778/3836663.3836718},
        url = {https://doi.org/10.14778/3836663.3836718},
        year = {2026}
}

Incoming Citations (Sorted by Pagerank)

Showing 0 of 0 citing papers.

Rank Citing Paper Year Venue Pagerank
Previous Page 1 / 1 Next

Outgoing Citations (Sorted by Pagerank)

Showing 1 of 1 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Rank Cited Paper Year Venue Pagerank
194 Milvus: A Purpose-Built Vector Data Management System 2021 SIGMOD 0.00025636725
Previous Page 1 / 1 Next

Semantically Similar Papers