Weekly IR Frontiers: IBM Proposes Hierarchical BM25 for Billion-Document Scale
_reachsumit · x · 2026-08-10
A curated list of the top Information Retrieval papers of the week (Vol.168), highlighting:
- Hierarchical BM25: IBM Research proposes a two-level index using LDA clustering to solve the 400GB memory footprint and slow queries of flat BM25 at a billion-document scale.
- Query-Adaptive Vector Search: Amazon introduces a robust vector search policy.
- Reranking for RAG: Liu et al. present rubric-guided reranking for deep research and RAG.
- Generative Retrieval: Snap Inc. explores LLM-based generative retrieval for content recommendation.
- Boolean Retrieval: Wang et al. exploit structure-aware Boolean retrieval for deep-research agents.
More from Research
- Netflix details its production LLM judge: hundreds of thousands of recommendations scored weekly — omarsar0 · 2026-08-24
- Nature Comment: Provenance, not interpretability, grounds trust in autonomous science — gabepgomes · 2026-08-24
- New Architecture RHEA: Train 1B Model on 8GB VRAM — zemondza · 2026-08-24
- Trained two 16M-param models to do generative CAD with real physics — debreuil · 2026-08-24
- Claude model helps discover complex structure on S^6, solving 60-year-old math problem — Singularitarian · 2026-08-24
- Study: Agents read instructions/notes 60.5% of the time, rarely touch API docs — dair_ai · 2026-08-24