Search

Microsoft Launches ‘Correction’, an AI Feature That Can Detect and Fix AI Hallucinations

Microsoft’s Correction feature is being added to Azure AI Content Safety’s groundedness detection system.

Advertisement
Highlights
  • Microsoft claims this capability will make AI’s responses more accurate
  • Correction can show an explanation after pinpointing incorrect text
  • To use the feature, users must connect AI systems to Azure
Microsoft Launches ‘Correction’, an AI Feature That Can Detect and Fix AI Hallucinations

AI hallucination is when an AI model generates incorrect or misleading information

Photo Credit: Reuters

Microsoft launched a new artificial intelligence (AI) capability on Tuesday that will identify and correct instances when an AI model generates incorrect information. Dubbed “Correction”, the feature is being integrated within Azure AI Content Safety's groundedness detection system. Since this feature is available only through Azure, it is likely aimed at the tech giant's enterprise clients. The company is also working on other methods to reduce instances of AI hallucination. Notably, the feature can also show an explanation for why a segment of the text was highlighted as incorrect information.

Microsoft “Corrections” Feature Launched

In a blog post, the Redmond-based tech giant detailed the new feature which is claimed to battle instances of AI hallucination, a phenomenon where AI responds to a query with incorrect information and fails to recognise its falsity.

The feature is available via Microsoft's Azure services. The Azure AI Content Safety system has a tool dubbed groundedness detection. It identifies whether a response generated is grounded in reality or not. While the tool itself works in many different ways to detect instances of hallucination, the Correction feature works in a specific way.

For Correction to work, users must be connected to Azure's grounding documents, which are used in document summarisation and Retrieval-Augmentation-Generation-based (RAG) Q&A scenarios. Once connected, users can enable the feature. After that, whenever an ungrounded or incorrect sentence is generated, the feature will trigger a request for correction.

Put simply, the grounding documents can be understood as a guideline that the AI system must follow while generating a response. It can be the source material for the query or a larger database.

Then, the feature will assess the statement against the grounding document and in case it is found to be misinformation, it will be filtered out. However, if the content is in line with the grounding document, the feature might rewrite the sentence to ensure that it is not misinterpreted.

Additionally, users will also have the option to enable reasoning when first setting up the capability. Enabling this will prompt the AI feature to add an explanation on why it thought that the information was incorrect and needed a correction.

A company spokesperson told The Verge that the Correction feature uses small language models (SLMs) and large language models (LLMs) to align outputs with grounding documents. “It is important to note that groundedness detection does not solve for ‘accuracy,' but helps to align generative AI outputs with grounding documents,” the publication cited the spokesperson as saying.

For the latest tech news and reviews, follow Gadgets 360 on X, Facebook, WhatsApp, Threads and Google News. For the latest videos on gadgets and tech, subscribe to our YouTube channel. If you want to know everything about top influencers, follow our in-house Who'sThat360 on Instagram and YouTube.

 
Show Full Article
Please wait...
Advertisement

Related Stories

Popular Mobile Brands
  1. Vodafone Idea (Vi) Rolls Out 5G Services in These Nine Cities
  2. Flipkart Freedom Sale 2025 to Start Tonight; Smartphone Deals Teased
  3. Qualcomm Said to be Developing Another High-End Snapdragon Chipset
  4. Amazon Freedom Sale 2025 Highlights: Best Deals on Phones, Tablets and More
  5. Nothing OS 4.0 Closed Beta for the Phone 3 Begins: Know How to Apply
  1. MIT Just Proved Einstein Wrong in the Famous Double-Slit Quantum Experiment
  2. PSR J0922+0638 Pulsar Keeps Glitching Every 550 Days, Scientists Are Intrigued
  3. Starlink’s Unintended Signals Threaten Astronomical Research, Study Finds
  4. DogMan OTT Release Date: When and Where to Watch This American Animated Movie Online?
  5. Love Hurts OTT Release Date: When and Where to Watch it Online?
  6. Xbox Game Pass Hit Nearly $5 Billion in Revenue for the First Time in FY 2025, Microsoft Says
  7. Samsung Tri-Fold Phone to Launch in H2 2025; Galaxy S25 FE Teased to Debut Earlier
  8. Flipkart Freedom Sale 2025 to Start Tonight With Discounts on iPhone 16, Galaxy S24, Nothing Phone 3a, More
  9. Vodafone Idea (Vi) 5G Services Rolling Out in Surat, Meerut, and Seven Other Cities With Special Introductory Offers
  10. Qualcomm Said to be Developing Another High-End Chipset; Could Offer Snapdragon 8 Elite-Level Performance
Gadgets 360 is available in
Download Our Apps
App Store App Store
Available in Hindi
App Store
© Copyright Red Pixels Ventures Limited 2025. All rights reserved.
Trending Products »
Latest Tech News »