Microsoft Launched a new Artificial Intelligence (AI) Capability on Tuesday that will identify and correct instals 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 instals of ai hallucination. Notable, the feature can also show an explanation for a segment of the text was highlighted as incorrect information.
Microsoft “Corrections” feature launched
In a blog postThe Redmond-Based Tech Giant Detailed The New Feature Which is Claimed to Battle Institutes of Ai Hallucination, A Phenomenon Where Ai Responds to a Query With Incorect Information and Fails to RECGNISE 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 institutions of hallucination, the correction feature work in a specific way.
For correction to work, users must be connected to azure’s grounding documents, which are used in document summarization and retrieval-augmentation-generation-based (rag) Q&A SCENARIOS. Once Connected, users can enable the feature. After that, whenever an unground or incorrect sentence is generated, the feature will trigger a request for correction.
Put simply, the grounding documents can be undersrstood as a guideline that AI System must Follow While Who 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.
Additional, users will also 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 information was incorrect and needed a correction.
A company specksperson 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 Citeed the Spokespens
(Tagstotranslate) Microsoft correction feature ai hallucination detection detection detection detection launched microsoft
