mlsanityData to 14 Oct 2026

WindTunnel -- A Framework for Community Aware Sampling of Large Corpora

arXiv 2410.20301 ↗First posted 27 Oct 2024cs.IRcited by 0

On the map: Retrieval-augmented generation → RAG pipeline design and evaluation

Abstract (arXiv)

Conducting comprehensive information retrieval experiments, such as in search or retrieval augmented generation, often comes with high computational costs. This is because evaluating a retrieval algorithm requires indexing the entire corpus, which is significantly larger than the set of (query, result) pairs under evaluation. This issue is especially pronounced in big data and neural retrieval, where indexing becomes increasingly time-consuming and complex. In this paper, we present WindTunnel, a novel framework developed at Yext to generate representative samples of large corpora, enabling efficient end-to-end information retrieval experiments. By preserving the community structure of the dataset, WindTunnel overcomes limitations in current sampling methods, providing more accurate evaluations.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RAG pipeline design and evaluation, one of 15 directions in Retrieval-augmented generation. Builds on 4 of its 13 references that are in the map. First posted on arXiv 27 Oct 2024.

Builds on

4 of 13 references.

References · 4

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2020MPNet: Masked and Permuted Pre-training for Language Understandingcited by 981
  3. 2016Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphscited by 861
  4. 2020Grale: Designing Networks for Graph Learningcited by 28

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Revisiting RAG Retrievers: An Information Theoretic Benchmark
  2. 2026BM25 Wins at Scale: A Scaling Study of Retrieval-Augmented Generation Paradigms
  3. 2025EraRAG: Efficient and Incremental Retrieval Augmented Generation for Growing Corpora
  4. 2026HAKARI-Bench: A Lightweight Benchmark for Comparing Retrieval Architectures and Efficiency Settings under Unified Conditions
  5. 2026DA-RAG: Dynamic Attributed Community Search for Retrieval-Augmented Generation
  6. 2024MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries
  7. 2025GRITHopper: Decomposition-Free Multi-Hop Dense Retrieval
  8. 2025Test-time Corpus Feedback: From Retrieval to RAG