PinnedAndrei LopatenkoLLMs and Search EnginesA set of notes on how search engines can leverage Large Language Models (LLMs) and generative AI for significant customer and business…6 min read·Apr 22, 2024----
PinnedAndrei LopatenkoOptimization problemsRecently, I travelled to Florida with my wife. When Airline assigned seats to the passengers, almost all families got seats remote from…10 min read·Apr 22, 2021--1--1
Andrei LopatenkoWiki version of the compendium of LLM Evaluation methods for conveniencehttps://github.com/alopatenko/LLMEvaluation/wiki/Compendium-of-LLM-Evaluation-methods1 min read·Apr 26, 2024----
Andrei LopatenkoWho validates the Validators: Evolution of EvaluationA new LLM evaluation paper from UC Berkeley Humans are good to evaluate LLMs, but human evaluation is hard to scale LLM evaluation of LLMs…2 min read·Apr 22, 2024----
Andrei LopatenkoHow Generative AI and Foundation Models Are Building Smarter Cities Exploring the FutureMy presentation for the UK-USA Smart City Forum centers on foundational and generative AI models. Given the 20-minute time constraint in…1 min read·Apr 20, 2024----
Andrei LopatenkoCompendium of LLM Evaluation methodsIn response to the need for a broader understanding of evaluation methods and the dissemination of best practices, I am creating a…1 min read·Apr 17, 2024----
Andrei LopatenkoEvaluation of LLMs and LLM ApplicationsPresentation download2 min read·Apr 1, 2024----
Andrei LopatenkoRetrieval Augmented Generation (RAG) and Fine-TSeveral recent papers comparing RAG vs Fine-Tuning in various settings There are different outcomes of these studies, but the aggregated…1 min read·Mar 18, 2024----