Hierarchical token pooling halves multi-vector indexes at 100.6% of BEIR performance
tomaarsen · x · 2026-08-18
The pain point of multi-vector retrieval is index size: 4,874 NQ passages become 608,414 token vectors — 311.5 MB vs 20 MB for a 1024d dense index, about 16x. HierarchicalTokenPooling (Clavié, Chaffin & Adams) clusters each document's token vectors with Ward linkage and keeps 1/poolfactor of them; at poolfactor=2 the index halves while retaining 100.6% of unpooled BEIR performance, usable per call, standalone, or baked into the model. The other escape routes: a real late-interaction index, or use it as a reranker.
Related event: Sentence Transformers v6.0 ships with first-class late interaction models(33 posts)→
More from coding & agent
- MUZIM workflow: local transcription and exact quote retrieval for bug tracking — CodeByPoonam · 2026-08-19
- Using AI Agents to draft release reports from evidence collections — CodeByPoonam · 2026-08-19
- Netlify integrates OpenRouter to enable model swapping without code changes — thisiskp_ · 2026-08-19
- Dev runs three Codex accounts plus Claude to parallelize coding agents — ChanceKelch · 2026-08-19
- DeepSeek open sources 'deepseek-harness' agent framework with 130k+ stars — alex_verem · 2026-08-19
- Cloud agents save hours vs local setups: a dev's parallel-workflow experience — brandon_galang · 2026-08-19