Concept library
638 concepts across 13 domains and 52 tracks. Each track is a coherent sequence — read it top to bottom or dip in wherever the gap is.
All domains
01Foundations
02Transformer Internals
03Training & Fine-Tuning
04Reinforcement Learning
05Inference, Systems & Hardware
06Applied LLM Engineering
07Reasoning, Evaluation & Safety
08Multimodal & Applications
09Classical ML & Statistical Learning
10Causal Inference & Experimentation
11Time Series & Forecasting
12Graphs, Recommenders & Structured Data
15Search & Information Retrieval
15
Search & Information Retrieval
Thirty years of ranking research that RAG rediscovered, usually the hard way.
4tracks
16concepts
226cards
1.9hreading
Classical Information Retrieval Inverted indexes, TF-IDF and BM25, query processing, and the lexical baselines that refuse to be beaten. 4 concepts · 60 cards
- 01 BM25 and Term Frequency Saturation Why a term appearing twenty times should not score ten times higher than one appearing twice, how BM25 encodes that as a saturating function, and what its two parameters actually control.
- 02 Inverted Indexes and Postings Lists The data structure that makes text search sublinear in corpus size, why postings are stored as sorted document IDs, and how gap encoding turns a list of integers into a few bits each.
- 03 Dynamic Pruning with WAND and Block-Max Retrieving the exact top-k without scoring most of the candidates, by maintaining an upper bound on what each document could score and skipping everything that cannot beat the current threshold.
- 04 Learned Sparse Retrieval Using a language model to assign weights over the vocabulary, including terms not present in the text, so semantic matching runs on an inverted index instead of a vector index.
Learning to Rank Pointwise, pairwise and listwise objectives, LambdaMART, position bias and counterfactual training. 4 concepts · 56 cards
- 01 Pointwise, Pairwise and Listwise Objectives Ranking is not regression, and the three families of learning-to-rank losses differ in how much of the ranking structure they put inside the objective rather than leaving to a sort.
- 02 Counterfactual Learning to Rank Training a ranker on logged clicks while correcting for the bias in how those clicks were generated, which turns a biased log into an unbiased estimate of a ranking objective.
- 03 LambdaRank and LambdaMART The trick of defining a gradient without ever defining a loss, which lets gradient boosting optimise a discontinuous ranking metric directly, and why the result dominated learning to rank for a decade.
- 04 Position Bias and the Examination Hypothesis Clicks measure relevance multiplied by the chance the user looked, so training on raw clicks teaches a ranker to reproduce whatever ranking generated the logs.
Query Understanding Intent classification, spelling and segmentation, expansion, rewriting, and conversational query resolution. 4 concepts · 56 cards
- 01 Query Intent and Taxonomies The same string can be three different requests, and classifying which one determines whether the right answer is a document, an entity, an action, or a generated response.
- 02 Spelling Correction and Query Segmentation Fixing what the user typed before matching it, where the hard part is not generating candidates but deciding whether the original was wrong at all.
- 03 Conversational Query Rewriting Turning a context-dependent follow-up into a self-contained query, which is what lets a stateless retriever serve a stateful conversation.
- 04 Query Expansion and Pseudo-Relevance Feedback Adding terms to a query to bridge vocabulary mismatch, and the drift failure that occurs when the terms are harvested from results that were wrong to begin with.
Search Evaluation Pooling and judgments, nDCG and MRR, interleaving, online metrics, and why offline gains vanish online. 4 concepts · 54 cards
- 01 Test Collections, Pooling and Judgment Bias The Cranfield paradigm made retrieval a measurable science, and the pooling shortcut that makes it affordable quietly penalises any system unlike the ones that built the pool.
- 02 nDCG, MRR and Graded Relevance The main ranking metrics differ in what they assume about the user, and choosing one is choosing a model of how far someone reads and what they are looking for.
- 03 Interleaving and Online Evaluation Mixing two rankers' results into a single list and attributing clicks gives a within-user paired comparison that detects differences far faster than an A/B test on the same traffic.
- 04 Why Offline Gains Vanish Online The recurring experience that an offline nDCG improvement produces no measurable online effect, and the four distinct mechanisms that cause it.