Fixing LLM Hallucinations with Facts

https://is1-ssl.mzstatic.com/image/thumb/Podcasts221/v4/0c/ee/8a/0cee8ace-73a2-029f-5973-7ec36cdb83d5/mza_4764223988593953722.jpg/600x600bb.jpg

AI Blindspot

Yogendra Miraje

15 episodes

1 week ago

AI blindspot is a podcast that explores the uncharted territories of AI by focusing on its cutting-edge research and frontiers

This podcast is for researchers, developers, curious minds, and anyone fascinated by the quest to close the gap between human intelligence and machines.

As AI is advancing at Godspeed, it has become increasingly difficult to keep up with the progress. This is a human-in-loop AI-hosted podcast.

Technology

RSS

All content for AI Blindspot is the property of Yogendra Miraje and is served directly from their servers with no modification, redirects, or rehosting. The podcast is not affiliated with or endorsed by Podjoint in any way.

Technology

https://d3t3ozftmdmh3i.cloudfront.net/staging/podcast_uploaded_nologo/42699973/42699973-1749102680268-62745bb0e3308.jpg

Fixing LLM Hallucinations with Facts

AI Blindspot

12 minutes 6 seconds

1 year ago

Fixing LLM Hallucinations with Facts

This episode explores how Google researchers are tackling the issue of "hallucinations" in Large Language Models (LLMs) by connecting them to Data Commons, a vast repository of publicly available statistical data.https://datacommons.org/The researchers experiment with two techniques: Retrieval Interleaved Generation (RIG), where the LLM is trained to generate natural language queries to fetch data from Data Commons and Retrieval Augmented Generation (RAG), where relevant data tables from Data...