Generative language models (LMs) are increasingly used for document class-prediction tasks and promise enormous improvements in cost and efficiency. Existing research often examines simple classification tasks, but the capability of LMs to classify on complex or specialized tasks is less well understood. We consider a highly complex task that is challenging even for humans: the classification of legal reasoning according to jurisprudential philosophy. Using a novel dataset of historical United States Supreme Court opinions annotated by a team of domain experts, we systematically test the performance of a variety of LMs. We find that generative models perform poorly when given instructions (i.e. prompts) equal to the instructions presented to human annotators through our codebook. Our strongest results derive from fine-tuning models on the annotated dataset; the best performing model is an in-domain model, LEGAL-BERT. We apply predictions from this fine-tuned model to study historical trends in jurisprudence, an exercise that both aligns with prominent qualitative historical accounts and points to areas of possible refinement in those accounts. Our findings generally sound a note of caution in the use of generative LMs on complex tasks without fine-tuning and point to the continued relevance of human annotation-intensive classification methods.

A new British artificial intelligence system can predict with up to 92% accuracy which people with memory problems will eventually develop dementia within the next two years. This is another indication that artificial intelligence has enormous potential that makes it possible to diagnose various diseases at an early stage. The goal is not only to diagnose impending dementia early, but also to reduce the number of people who are misdiagnosed with dementia. Researchers at the University of Exeter, led by Professor David Llewellyn, who published the study in the American medical journal JAMA Network Open, used data from 15,307 people with an average age of 72 with memory problems (of whom 1,568 had been diagnosed with Alzheimer's disease or another form of Alzheimer's disease). The "intelligent" system has learned to detect clues hidden in the data, which the human eye, even a neurologist or other specialist, cannot recognize.

Artificial intelligence can predict which people who attend memory clinics will develop dementia within two years with 92 percent accuracy, a largescale new study has concluded. Using data from more than 15,300 patients in the US, research from the University of Exeter found that a form of artificial intelligence called machine learning can accurately tell who will go on to develop dementia. The technique works by spotting hidden patterns in the data and learning who is most at risk. The study, published in JAMA Network Open and funded by funded by Alzheimer's Research UK, also suggested that the algorithm could help reduce the number of people who may have been falsely diagnosed with dementia. The researchers analyzed data from people who attended a network of 30 National Alzheimer's Coordinating Center memory clinics in the US.

Artificial intelligence can predict which people who attend memory clinics will develop dementia within two years with 92 per cent accuracy, a largescale new study has concluded. Using data from more than 15,300 patients in the US, research from the University of Exeter found that a form of artificial intelligence called machine learning can accurately tell who will go on to develop dementia. The technique works by spotting hidden patterns in the data and learning who is most at risk. The study, published in JAMA Network Open and funded by funded by Alzheimer's Research UK, also suggested that the algorithm could help reduce the number of people who may have been falsely diagnosed with dementia. The researchers analysed data from people who attended a network of 30 National Alzheimer's Coordinating Center memory clinics in the US.

Artificial intelligence can predict Alzheimer's at least two years in advance, according to new research. The technique works by spotting hidden patterns in the data and learning who is most at risk. A study involving more than 15,300 people found it was 92 percent accurate. The neural network would change the way dementia is diagnosed - helping doctors detect it sooner. Treatments would start much earlier.

Taking a page from David Letterman, a trio of panelists from Jobvite today outlined a top 10 list to HR Technology Conference and Exposition about what talent acquisition will look like in the months and years ahead. In its presentation, Tomorrow's Talent Acquisition, Today: The AI, Analytics and Automation Top 10, the Jobvite team laid out how those technologies can be used today to create better candidate journeys, more efficient recruiting processes and measurable, data-driven outcomes for a talent acquisition organization. The presenters were Zach Linder, vice president, analytics and machine learning; Morgan Llewellyn, chief data officer; and Dwaine Maltais CEO of Talentegy, which was recently acquired by Jobvite, a talent acquisition technology provider headquartered in Indianapolis. Click here to sign up for HRE's daily newsletters. In descending order, Jobvite's top 10 ways that AI, analytics and automation will reshape TA, by enabling HR and TA leaders, are: For example, Llewellyn outlined why there is a "real business case" to be made for why your organization should be more diverse and more inclusive, apart from the legal concern for many organizations.