Weaviate Podcast: Why "Retrieve More, Rerank" might be wrong
CShorten30 · x · 2026-08-17
The Weaviate Podcast episode 141 features Mathew Jacob, author of "Drowning in Documents". This paper challenges the common intuition in RAG to "retrieve more documents, then rerank". The discussion covers:
- Why increasing retrieval count might not help final performance.
- Full scoring mechanisms and cross-encoders.
- Phantom hits.
- Listwise Rerankers.
- Ranking Cascades.
It is a deep technical exploration into optimizing large-scale retrieval systems.
More from Research
- UCSD Researchers Propose Dataset Watermarking Detectable via Black-Box API Access — yuxiangw_cs · 2026-10-16
- EmbodiedEvo tops RoboDojo as agents inherit reusable skills and lessons — Aiden_Tech_Ai · 2026-10-16
- CHI reviewer laments: papers' Discussion sections now cite nothing — IanArawjo · 2026-10-16
- Casper: Understanding 90% of neurons ≠ understanding the network — StephenLCasper · 2026-10-16
- NVIDIA Launches cuPotential in CUDA-X to Bring AI Agents to Semiconductor Materials Simulation — tomaszbednarz · 2026-10-16
- Agentic Search Systems Are Rewarded Only for Final Answers, Raising Faithfulness Concerns — burkov · 2026-10-16