---
title: "Can Microsoft’s New AI Correction Feature Fix Hallucinations?"
description: "Microsoft Claims New Feature Can Detect and Correct AI-Generated False Statements Microsoft claims to have developed a new capability that detects and corrects false or misleading statements..."
url: https://brandligo.com/can-microsofts-new-ai-correction-feature-fix-hallucinations/
date: 2024-09-27
modified: 2024-09-27
author: "Junaid Abro"
image: https://brandligo.com/wp-content/uploads/2024/09/1200x675_cmsv2_84805771-deb3-5fb3-a8d0-24e2f350211d-8755800.webp
categories: ["Tech News"]
tags: ["AI", "analytics", "decision-making", "ethics efficiency", "healthcare", "improvement misinformation", "innovation data", "insights medicine", "productivity", "technology", "trust"]
type: post
lang: en
---

# Can Microsoft’s New AI Correction Feature Fix Hallucinations?

## Microsoft Claims New Feature Can Detect and Correct AI-Generated False Statements

Microsoft claims to have developed a new capability that detects and corrects false or misleading statements generated by AI.

This week, Microsoft introduced a new artificial intelligence ([AI](https://brandligo.com/the-ai-skills-challenge-achievement-unlocked/)) feature designed to address inaccurate outputs from AI models.

The new “Correction” capability will detect and correct errors in AI-generated content, according to the tech giant.

These so-called AI hallucinations will be fixed in real-time “before users of generative AI applications encounter them,” Microsoft stated, with a spokesperson describing it as a “first-of-its-kind capability.”

The feature works by scanning and highlighting inaccurate parts of a response. It can then explain why the segment is incorrect and use generative AI to rewrite it, ensuring the revised content “better aligns with connected data sources,” according to a Microsoft representative.

This feature is part of [Microsoft’s Azure](https://brandligo.com/latest-new-for-global-windows-outage-grounds-flights-hits-banks-and-media-businesses/) AI Content Safety software, which can now also be embedded on devices.

## Why does AI hallucinate?

AI models are trained on large datasets to make predictions, but they can sometimes “hallucinate,” meaning they produce false or inaccurate statements. This often happens due to incomplete or biased training data.

Jesse Kommandeur, a strategic analyst at the Hague Centre for Strategic Studies, likens it to baking a cake without a full recipe—where you rely on past experiences to make educated guesses. Sometimes the result is good, but other times it fails.

“The AI is essentially trying to ‘bake’ the final output (like a text or decision) using the incomplete ‘recipes’ it has learned,” Kommandeur explained in an email.

There have been several high-profile instances where AI chatbots have given false or misleading answers. For example, some lawyers submitted fake legal cases after using AI models, and earlier this year, [Google’s AI](https://gemini.google.com/) summaries were found to provide inaccurate information.

A 2023 analysis by the company Vectara revealed that AI models hallucinated between 3% and 27% of the time, depending on the tool. Additionally, the non-profit Democracy Reporting International warned ahead of the European elections that none of the most popular chatbots delivered “reliably trustworthy” answers to election-related questions Microsoft’s AI.

## Could this new tool address the issue of hallucinations?

“Generative AI doesn’t truly reflect, plan, or think; it simply responds sequentially to inputs. We’ve seen the limitations of this approach,” said Vasant Dhar, a professor at New York University’s Stern School of Business and Center for Data Science.

“While it’s possible that the new correction capability will reduce hallucinations, it’s virtually impossible to eliminate them completely with the current architecture,” he noted. Ideally, Dhar said, a company would aim to claim a reduction in a specific percentage of hallucinations.

“That would necessitate a substantial amount of data on known hallucinations, along with testing to determine if this prompt engineering method effectively reduces them Microsoft’s AI. That’s quite a demanding task, which is why they haven’t made any quantitative claims about how much it reduces hallucinations,” he said.

Kommandeur reviewed a paper that Microsoft confirmed was published regarding the correction feature. He noted that while it “appears promising and employs a methodology I haven’t seen before, it’s likely that the technology is still evolving and may have its limitations Microsoft’s AI.”

## Gradual Enhancements

Microsoft acknowledges that hallucinations in [AI](https://brandligo.com/the-ai-skills-challenge-achievement-unlocked/) models have hindered their use in critical fields like medicine and their overall deployment.

“All these technologies, including Google Search, are in a phase of continuous incremental improvement once the core product is established,” said Dhar.

“In the long run, I believe that investing in AI could become problematic if the models continue to hallucinate, as these errors may lead to misinformation and flawed decision-making,” noted Kommandeur.

“However, in the short term, I think large language models (LLMs) provide significant value in daily life, enhancing efficiency, which makes us somewhat overlook the issue of hallucinations,” he added.

######