Why "Retrieve More, Rerank" is Wrong? Deep Dive on Drowning in Documents Paper
CShorten30 · x · 2026-08-17
This episode of the Weaviate Podcast features Mathew Jacob discussing his paper "Drowning in Documents" from Databricks. It challenges the conventional wisdom of "retrieve more, rerank, get better results," suggesting this approach often fails. The discussion covers the paper's insights on why simply increasing retrieval volume doesn't work and how it influences Weaviate's exploration of scaling reranked retrieval systems.
More from Research
- GAE paper learns a geometry-native latent space for 3D-consistent world generation — yshan2u · 2026-10-16
- Agents turn conservative as context grows: edits shrink from 150 to 30 lines — dbreunig · 2026-10-16
- LMR-BENCH at EMNLP 2025 tests whether LLM agents can reproduce real LLM research — ZhiyuChen4 · 2026-10-16
- Ex-OpenAI researcher claims most neurons are legible now; critics call it hype — anshulkundaje · 2026-10-16
- Physicist pushes back on ML community's acceptance that models may be beyond understanding — tszzl · 2026-10-16
- Survey: AI agent evaluation is getting realistic but still fails to measure safety and reliability — burkov · 2026-10-16