Free open book "How Search Decides What You See" covers retrieval from Boolean to dense
burkov · x · 2026-11-15
Aaron Tay Chee Hsien's free open book (2026), readable online on ChapterPal, builds from Boolean retrieval and inverted indexes through BM25-ranked lexical search, learned representations and dense retrieval, then contrasts single-vector retrieval with learned sparse methods, token-level comparison, reranking, diversification, and ranked-list fusion. Throughout, it distinguishes a representation from a scoring method, a retrieval stage from a ranking stage, and a product label from evidence about the machinery underneath.
More from Research
- dspy-wsp Lets a Frontier LLM Edit Small Model Weights Directly: +18.3 Pts for ~$5-8 per Run — stanfordnlp · 2026-11-16
- Song Han Team Proposes Coco, a Proactive Desktop Agent with On-Device Context Observation — stanfordnlp · 2026-11-16
- Ceci n'est pas le benzène: how chemical representations mislead ML in drug discovery — CatAstro_Piyush · 2026-11-16
- Science Prediction Universe benchmark: best agents score just 0.486 at predicting wet-lab outcomes — liangchen5518 · 2026-11-16
- Expected Value framework: turning ML predictions into measurable ROI — mdancho84 · 2026-11-16
- ML predictions as probabilities: the foundation for business data science — mdancho84 · 2026-11-16