Microsoft’s StudentSim Turns Tutor Testing Into a Fidelity Question, With Guidance Graded Against an Answer Key
Microsoft Research’s StudentSim trains one simulated student per...
Browse Tag
LLM Evaluation
7 Articles
Microsoft’s ThinkingBox Turns AI Agent Scores Into a Database Audit, Repeated 20 Times
Microsoft and Hugging Face’s ThinkingBox grades AI agents on the...
How to Measure Whether Cross-Encoder Reranking Actually Improves RAG Retrieval
A step-by-step Python tutorial that builds a cross-encoder...
How to Calibrate an LLM-as-Judge Against Human Ratings With Cohen’s Kappa
A hands-on Python tutorial that validates a local LLM judge...
How to Automatically Tune RAG Chunk Size and Top-K With a Local Eval Harness
Build a local evaluation harness that measures real RAG...
How to Build a Local LLM-as-a-Judge Evaluation Harness for AI Agents
Learn how to build a Python evaluation harness that grades AI...
LLM Groupthink Makes AI Creativity an Evaluation Problem
MIT Technology Review’s LLM groupthink reporting shows why AI...