• Menu
  • Skip to right header navigation
  • Skip to main content
  • Skip to primary sidebar

DigiBanker

Bringing you cutting-edge new technologies and disruptive financial innovations.

  • Home
  • Pricing
  • Features
    • Overview Of Features
    • Search
    • Favorites
  • Share!
  • Log In
  • Home
  • Pricing
  • Features
    • Overview Of Features
    • Search
    • Favorites
  • Share!
  • Log In

Vectara offers to reduce hallucination rates in enterprise AI systems to about 0.9%; provides detailed explanation for factual inconsistency along with a corrected version

May 14, 2025 //  by Finnovate

AI agent and assistant platform provider Vectara launched a new Hallucination Corrector directly integrated into its service, designed to detect and mitigate costly, unreliable responses from enterprise AI models. In its initial testing, Vectara said the Hallucination Corrector reduced hallucination rates in enterprise AI systems to about 0.9%. The HHEM scores the answer against the source with a probability score between 1 and 0, where 0 means completely inaccurate – a total hallucination – and 1 for perfect accuracy. HHEM is available on Hugging Face and received over 250,000 downloads last month, making it one of the most popular hallucination detectors on the platform. In the case of a factually inconsistent response, the Corrector provides a detailed output including an explanation of why the statement is a hallucination and a corrected version incorporating minimal changes for accuracy. The company automatically uses the corrected output in summaries for end-users, but experts can use the full explanation and suggested fixes for testing applications to refine or fine-tune their models and guardrails to combat hallucinations. It can also show the original summary but use corrections info to flag potential uses while offering the corrected summary as an optional fix. In the case of LLM answers that fall into the category of misleading but not quite outright false, the Hallucination Corrector can work to refine the response to reduce its uncertainty core according to the customer’s settings.

Read Article

Category: AI & Machine Economy, Innovation Topics

Previous Post: « Web browsers, by including agentic AI capabilities (capable of understanding context, automating and executing multi-step tasks), can access information without any tabs, clicking or scrolling
Next Post: Pega launches agents for workflow and decisioning design that can instantly create out-of-the-box conversational agents from any workflow »

Copyright © 2025 Finnovate Research · All Rights Reserved · Privacy Policy
Finnovate Research · Knyvett House · Watermans Business Park · The Causeway Staines · TW18 3BA · United Kingdom · About · Contact Us · Tel: +44-20-3070-0188

We use cookies to provide the best website experience for you. If you continue to use this site we will assume that you are happy with it.