FeaturedSemiconductor
The highly-technical vocabulary of the semiconductor industry requires models with specialized training, provided with direct access to rich, multimodal data and complex documents.
Read moreFeaturedSemiconductorCategories
Blog - Hallucination - Page 3
All posts
Cut the Bull... Detecting Hallucinations in Large Language Models
Vectara launches the open source Hughes Hallucination Evaluation Model (HHEM) and uses it to compare hallucination rates across top LLMs including OpenAI, Cohere, PaLM, Anthropic’s Claude 2 and more.
How Vectara's New Boomerang Model Takes Retrieval Augmented Generation to the Next Level via Grounded Generation
Learn about the benefits of Vectara’s new embedding model “Boomerang,” including how our version of Retrieval Augmented Generation (RAG), called Grounded Generation, is smarter than other systems
Retrieval Augmented Generation: Making Generative AI Safe, Trustworthy, and More Relevant
While generative AI is a powerful technique that promises to revolutionize how we interact with computers, it has serious drawbacks. Vectara’s Retrieval Augmented Generation approach addresses those drawbacks, making generative AI safer and more cost-effective to use.
New Release: “Grounded Generation”
Get accurate, dependable answers from your data with fewer hallucinations
Avoiding hallucinations in LLM-powered Applications 12
LLM hallucinations and how to avoid them with Grounded Generation