Microsoft's New AI Correction Feature Aims to Tackle Hallucinations

The End of AI Hallucinations? Microsoft's 'Correction' Feature

Microsoft recently announced an AI feature called "Correction," which detects and corrects AI hallucinations. Hallucinations are cases where AI models give out false or misleading information. This feature is being added to the system for detecting the AI's groundedness. AI's groudedness is nothing but its ability to be in touch with reality. Azure AI Content Safety will have this feature to make sure AI gives accurate answers. The new Microsoft feature, Correction, is specifically engineered to identify incorrect or unreal statements produced by AI systems in real-time. The feature as its name describes will correct such wrongful information to enhance user experience. Correction Besides grounding documents would be a resource base that AI models use as a repository. This would help ensure the output matches factual data. Whenever the AI system generates a response, the grounding system checks whether the information produced is correct or contains errors. Correction will thus trigger a review if they do detect any misinformation, providing rightful suggestions. Moreover, the user would get control over choosing a reasoning explanation that describes why the AI system flagged specific content as wrong. This would help make the correction process more transparent.

Could Microsoft's new AI feature really correct hallucinations?

Microsoft claims it has a new capability that detects and corrects false or misleading statements from AI. Microsoft unveiled a new artificial intelligence (AI) feature this week that it says will help to correct models' false statements. The new "Correction" capability will identify AI output inaccuracies and fix them, according to the technology giant. So-called AI hallucinations will be corrected in real-time "before users of generative AI applications encounter them," Microsoft said, with a spokesperson calling it a "new first-of-its-kind capability". The feature works by scanning and highlighting the inaccurate part of a response. It can then generate a response about why the segment is wrong and use generative AI to correct the section to make sure "that the rewritten content better aligns with connected data sources," a Microsoft spokesperson said. It's a part of Microsoft's Azure AI Content Safety software interface, which can also now be embedded on devices. AI models are trained on extensive datasets to make predictions, but they can also "hallucinate," which means they generate incorrect or false statements. This can be due to incomplete or biased training data. Jesse Kommandeur, a strategic analyst at the Hague Centre for Strategic Studies, compares it to baking a cake without the full recipe - where you guess based on prior experiences what may work. Sometimes the cake comes out well but other times it doesn't. "The AI is trying to 'bake' the final output (like a text or decision) based on incomplete information ('recipes') it has learned from," Kommandeur said in an email. There have been many high-profile examples of AI chatbots providing false or misleading answers, from lawyers submitting fake legal cases after using an AI model to Google's AI summaries providing misleading and inaccurate responses earlier this year. An analysis by the company Vectara last year found that AI models hallucinated between 3 and 27 per cent of the time depending on the tool. Meanwhile, non-profit Democracy Reporting International said ahead of the European elections that none of the most popular chatbots provided "reliably trustworthy" answers to election-related queries. Generative AI "doesn't really reflect and plan and think. It just responds sequentially to inputs... and we've seen the limitations of that," said Vasant Dhar, a professor at New York University's Stern School of Business and Center for Data Science in the US. "It's one thing to say [the new correction capability] will reduce hallucinations. It probably will, but it's really impossible to get it to eliminate them altogether with the current architecture," he added. Ideally, Dhar added, a company would want to be able to claim it reduces a certain percentage of hallucinations. "That would require a huge amount of data on known hallucinations and testing to see if this little prompt engineering method actually reduces them. That's actually a very tall order, which is why they haven't made any kind of quantitative claim about how much it reduces hallucinations". Kommandeur looked at a paper Microsoft confirmed was published about the correction feature and said while it "looks promising and chooses a methodology I haven't seen before, it's likely that the technology is still evolving and may have its limitations". Microsoft says hallucinations have held back AI models in high-stakes fields. such as medicine, as well as for their broader deployment. "All of these technologies including Google Search are technologies where these companies just continue to make incremental improvements in the product," said Dhar. "That's kind of the mode once you have the main product ready, then you keep improving it," he said. "From my perspective, in the long term, investment in AI can become a liability if the models keep hallucinating, especially if these errors keep leading to misinformation, flawed decision-making etc," said Kommandeur. "In the short term, however, I think the [large language models] LLMs add so much value to the daily lives for a lot of people in terms of efficiency, that the hallucinations are something we seem to take for granted," he said.