Stopping Hallucinations From Hurting Your LLMs // Atindriyo Sanyal // LLMs in Prod Conference Part 2

This portion is sponsored by Galileo.
Website: https://www.rungalileo.io
Galileo is an ML Data Intelligence company, that helps detect critical errors in your machine learning data and labels, and quickly fixes them to get high-quality models in record time. Support NLP, CV, Tabular data, and LLM use cases.

//Abstract
This talk is all about quantifying hallucinations -- the most critical evaluation metric for LLMs. In this talk, we'll dive deeper into what Hallucinations mean in modern-day LLM workflows, and how they …

conference data data intelligence errors galileo hallucinations intelligence labels llm llms machine machine learning machine learning data nlp part prod quality sponsored support tabular tabular data them