Trang chủ / Tin tức / Khoa học & công nghệ
Khoa học & công nghệ

Beyond Benchmark Scores: How Synthetic and Authentic Query Distributions Diverge in RAG Evaluation

03/11/2026 · Thành viên: Ông. Nguyễn Việt Anh · Nguồn: OpenAlex

RAG systems are routinely evaluated using synthetic question sets generated from the target document corpus. While this practice provides a useful check on overall retrieval capability, relying exc...

<p><strong>Tác giả:</strong> Filip J. Kucia, Barbara M. Gawlik</p>

<p>RAG systems are routinely evaluated using synthetic question sets generated from the target document corpus. While this practice provides a useful check on overall retrieval capability, relying exclusively on synthetic benchmarks can mislead under distribution shift and overstate deployment readiness. Synthetic generation spreads questions evenly across the corpus, formulating long, detailed queries; real users put most of their traffic on a few administrative and procedural topics in short q...</p>

<p>📄 DOI: <a href="https://doi.org/https://doi.org/10.1145/3799682.3839970" target="_blank" rel="noopener">https://doi.org/10.1145/3799682.3839970</a></p>

<p>📖 <a href="https://doi.org/https://doi.org/10.1145/3799682.3839970" target="_blank" rel="noopener">Xem bài báo đầy đủ</a></p>

Bài viết được biên soạn lại bởi LIFVietnam. Nguồn tham khảo: OpenAlex