Stanford University released a study on generative AI legal research tools from LexisNexis and Thomson Reuters, finding that they deliver hallucinated results more often than claimed. The study has faced criticism for comparing different products and not testing one of Thomson Reuters’ AI platforms. Thomson Reuters has now made the product available to the researchers, and they will update their results accordingly. The study challenges claims about reducing hallucinations through the use of retrieval-augmented generation.
Source: Law Sites
Leave a Reply