InData Science CollectivebyJulia Winn·Jun 3, 2025The Foundational Work Behind AI Success Most Teams SkipI haven’t had a surprise after an AI product launch in over 5 years. Here’s why.
Yash Vardhan Singh·May 24, 2025Not Just the Output: A Smarter Way to Evaluate AI Agent SystemsAI Agents have become another buzzword in the data science community. With growing adoption across industries, many teams are now building…
Ali Akram·Apr 28, 2025⚖️ Using LLMs as Judges with Azure OpenAI (QUICK)We need a way to quickly assess how bad our models are, so software engineers can keep their jobs. To get the reliability and effectiveness…
InGoPenAIbyArXiv In-depth Analysis·Mar 5, 2025MultiAgentBench: the first Comprehensive Benchmark for LLM agents evaluating both Collaboration…MultiAgentBench is a modular and extensible framework designed to facilitate the development, testing, and evaluation of multi-agent…
Dr. Ehoneah Obed·Feb 20, 2025Should You Trust a Health App Just Because It’s on the Market?A health app appears in the App Store. It has thousands of downloads, a polished interface, and glowing user reviews. Maybe it’s even being…
InData Science + AI at MicrosoftbyJuhi Singh·Nov 12, 2024Evaluating the unseen: Hybrid evaluation methodology for assessing the NLP algorithms without…By Juhi Singh, Bonnie Ao, and Sebastian Antinome
InArtificial Intelligence in Plain EnglishbyAmit Jangir·Nov 7, 2024How to Choose the Right Evaluation Metric for Your ModelWhen building and training machine learning models, selecting the right evaluation metric is a crucial step that can significantly impact…
Riaz Laghari·Oct 16, 2024Envisioning 2050 — The Futures of AssessmentOutline: “Envisioning 2050 — The Futures of Assessment”
Shrividya Subramaniam·Sep 24, 2024Out-of-Bag Evaluation: Evaluation without a Validation SetWe have all heard about the K-fold cross-validation technique to evaluate the performance of different machine learning models and prevent…
