Weaviate Podcast #150: Chess-Elo-style zELO behind SOTA zerank-2 reranker
CShorten30 · x · 2026-11-09
Weaviate Podcast #150 hosts ZeroEntropy co-founder Ghita Houir Alami (now leading model research at Notion) for a deep dive on search and reranking. ZeroEntropy's zELO borrows from chess Elo: a sparse sample of pairwise document battles is enough to fit absolute scores via a Thurstone model, then distilled into a pointwise reranker — yielding the state-of-the-art zerank-2 cross-encoder. Also covered: using cross-encoders to prune and classify results rather than just order them, and reranking with Jev / Decision Models.
Related event: Weaviate Podcast 150: ZeroEntropy Co-founder on Elo-based Reranking(2 posts)→
More from Research
- Toby Ord: log-log graphs mislead on power laws — METR time horizon is a case in point — tobyordoxford · 2026-11-10
- Epoch AI researcher: most 'algorithmic progress' in frontier AI may come from better data — S_OhEigeartaigh · 2026-11-10
- Qdrant presents vector index-native relevance feedback in production at CIKM Rome — qdrant_engine · 2026-11-10
- Meta's LLM-generated failing tests catch 74 privacy SEVs, cutting incidents 20% — Meta_Engineers · 2026-11-10
- Toby Ord: time delays in the intelligence feedback loop rule out a true singularity — tobyordoxford · 2026-11-10
- Cornell professor recruiting Fall 2027 PhD students in probabilistic ML, AI4Science — dianarycai · 2026-11-10