PinnedPublished inTDS ArchiveOverview of Supervised Machine Learning AlgorithmsHow the big picture gives us insights and a better understanding of ML by connecting the dotsJan 18, 2022A response icon6Jan 18, 2022A response icon6
PinnedPublished inTDS ArchiveMachine Learning in Three Steps: How to Efficiently Learn ItPrioritizing the Essentials for Predictive Modeling without Overwhelming YourselfMar 3, 2023A response icon2Mar 3, 2023A response icon2
How Large Language Models (LLMs) Learn: A Detailed BreakdownPre-training, SFT, and RLHF: Understanding the Step-by-Step Evolution of Conversational AINov 2Nov 2
Published inData Science CollectiveCalibrating Pareto Tails in InsuranceSeverity, Frequency, and Exposure NormalizationOct 29Oct 29
Published inAI AdvancesBeyond Standard RAG: A Structured Pipeline for Document Q&AMaybe you already tried RAG, but the answers were strange or not clear. Don’t worry — many people have the same problem.Oct 15Oct 15
Published inData Science CollectiveBeyond the Naïve RAG: A Human-Centered ApproachLessons from Building Chat-with-Document ApplicationsSep 20Sep 20
Building a Decision-Tree Chatbot for Document Question-AnsweringChatbots are no longer limited to casual conversations. In many organizations, teams need a reliable assistant that can answer precise…Sep 19Sep 19
Published inAI AdvancesRAG with Source Location Built InHelping Users Verify Answers in the Original TextApr 4A response icon3Apr 4A response icon3
Published inTowards AIStructured Document Comparison: Going Beyond Naive RAGFrom Precise Extraction to Transparent Justification using Advanced MethodsMar 27A response icon2Mar 27A response icon2
Published inAI AdvancesBuilding Trust in LLM Answers: Highlighting Source Texts in PDFs100% accuracy isn’t everything: helping users navigate the document is the real valueDec 27, 2024A response icon25Dec 27, 2024A response icon25