“Recall, precision, and baselines: how to read a model's score”TechRecall, precision, and baselines: how to read a model's score박기현·October 17, 2026evaluationllmmachine learning+2
“Data splits, leakage, and imbalance: why scores look better than they are”TechData splits, leakage, and imbalance: why scores look better than they are박기현·October 17, 2026evaluationmachine learningAI+1
“How LLMs Work, Where They Fail, and How to Verify Them”TechHow LLMs Work, Where They Fail, and How to Verify Them박기현·October 14, 2026evaluationllmAI+1
