FeaturedHallucination
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.
Read moreFeaturedHallucinationCategories
Blog - page 5
All posts
Tackling the Bull: Data Council Assembles the Braintrust to Tackle the Biggest Problems in Data and AI
A recap of this years Data Council conference and the Lightning Track that Vectara hosted
Gen AI Platform Build vs Buy – Part I: Options and Tradeoffs
When running Gen AI applications, it is important to decide whether to build or buy the RAG infrastructure on which to run your application. This article helps you to make that decision.
HHEM v2: A New and Improved Factual Consistency Scoring Model
Featuring multilinguality, unlimited context window, and calibration – The Hughes Hallucination Evaluation Model (HHEM) v2 is a major upgrade from v1
Do Smaller Models Hallucinate More?
Why the size of the model does not necessarily determine its likelihood to hallucinate
How Sankofa was Built with Vectara
Leveraging Vectara’s API to build Sankofa, a browser extension that allows anyone to chat with their web content history
Building GenAI Enterprise Applications with Vectara and Datavolo
Building a Datavolo data flow to process and index documents and messages into Vectara’s GenAI Platform
Say Goodbye to Delays: Expedite Your Experience with Stream Query
Discover how Stream Query reduces latency by delivering Gen AI responses in real-time chunks, eliminating the frustration of waiting for LLM’s response
Evaluating RAG with RAGAs
How to measure the quality of your Vectara RAG pipeline with RAGAs
April Fools Prank: New No-hallucinations LLM
A new LLM achieves 0% hallucinations and is set to revolutionize RAG
Before you go...Connect with
Connect with
our Community!
- Join us on Discord
Discord.
Connect our community channel.
- Join us on Github
Github.
Join our discussion channel.
- Follow us on X / Twitter
X / Twitter.
Get news, company information.
- Follow us on LinkedIn
LinkedIn.
Adopt best practices in projects.
- Join us on Discuss
Discuss.
Suggest your own ideas.
- Write us on E-mail
E-mail.
Ask your follow-up questions.
