Published inTowards Data ScienceUnderstanding and Mitigating LLM HallucinationsLLM hallucination detection challenges and a possible solution presented in a prominent research paperOct 23, 20234Oct 23, 20234
Published inTowards Data Science7 Ways to Monitor Large Language Model BehaviorSeven ways to track the evolution of LLMs with LangKit and WhyLabsJul 28, 20232Jul 28, 20232
Published inTowards Data SciencePerformance Estimation Techniques for Machine Learning ModelsAn overview of tools and methods to estimate performance of your ML modelMar 2, 2023Mar 2, 2023
Published inTowards Data ScienceUnderstanding Kolmogorov-Smirnov (KS) Tests for Data Drift on Profiled DataData drift meets data profilingDec 14, 2022Dec 14, 2022
Published inGoogle Cloud - CommunityAccelerating Question Answering Applications with MobileBERT and TFLiteThe world of Natural Language Processing has been evolving rapidly with the use of pre-trained, self-supervised models. However…Nov 22, 2021Nov 22, 2021
Published inTowards Data ScienceDeploy and Monitor your ML Application with Flask and WhyLabsImproving Observability for your AI SystemNov 3, 2021Nov 3, 2021
Published inTowards Data ScienceDon’t Let Your Data Fail YouContinuous Data Validation with whylogs and Github ActionsJul 12, 2021Jul 12, 2021
Published inTowards Data ScienceMonitoring and Retraining your Machine Learning ModelsWith Google Data Studio, lakeFS and Great ExpectationsMar 4, 20212Mar 4, 20212
Published inTowards Data ScienceDeploying a Fake News Detector Web Application with Google Cloud Run and FlaskWhile taking technical debt into considerationJan 20, 2021Jan 20, 2021
