This material may not be published, broadcast, rewritten, or redistributed. Quotes displayed in real-time or delayed by at least 15 minutes. Market data provided by Factset . Powered and implemented by FactSet Digital Solutions . Mutual Fund and ETF data provided by LSEG . Chinese humanoid robot breaks Usain Bolt's 100m dash record at 9.39 seconds World's first solar-powered ambulance brings healthcare off-grid The scammer at your doctor's office may already know who you are Kurt'CyberGuy' Knutsson recalls being stuck in New Orleans during Hurricane Katrina Cybercrime a global problem, thieves go for'targets of opportunity,' expert says Steve Doocy explores the US Air Force Academy's elite military training Supporting data centers is'perilous' politically: Brian Kilmeade Are American workers really using AI? Dr. Drew breaks down whether social media use qualifies as a true medical addiction Kurt'CyberGuy' Knutsson recalls being stuck in New Orleans during Hurricane Katrina Twenty-one years after Hurricane Katrina, Kurt CyberGuy Knutsson shares his experience surviving the storm. NEW You can now listen to Fox News articles!

The storm, which is set to make landfall in Jamaica Tuesday, has stunned meteorologists with its intensity and the speed at which it built. Meteorologists who have spent the past few days monitoring the rapid development of Hurricane Melissa in the Atlantic Ocean are sounding the alarm about the storm, which is set to make landfall in Jamaica today as a Category 5 hurricane. The sustained--and growing--intensity of the storm is remarkable, experts say, and has the makings of a historic hurricane. "When I look at the cloud pattern, I will tell you as a meteorologist and professional--and a person--it is beautiful, but it is terrifying," says Sean Sublette, a meteorologist based in Virginia. "I know what is underneath those clouds."

Recent work on explainable NLP has shown that few-shot prompting can enable large pretrained language models (LLMs) to generate grammatical and factual natural language explanations for data labels. In this work, we study the connection between explainability and sample hardness by investigating the following research question - "Are LLMs and humans equally good at explaining data labels for both easy and hard samples?" We answer this question by first collecting human-written explanations in the form of generalizable commonsense rules on the task of Winograd Schema Challenge (Winogrande dataset). We compare these explanations with those generated by GPT-3 while varying the hardness of the test samples as well as the in-context samples. We observe that (1) GPT-3 explanations are as grammatical as human explanations regardless of the hardness of the test samples, (2) for easy examples, GPT-3 generates highly supportive explanations but human explanations are more generalizable, and (3) for hard examples, human explanations are significantly better than GPT-3 explanations both in terms of label-supportiveness and generalizability judgements. We also find that hardness of the in-context examples impacts the quality of GPT-3 explanations. Finally, we show that the supportiveness and generalizability aspects of human explanations are also impacted by sample hardness, although by a much smaller margin than models. Supporting code and data are available at https://github.com/swarnaHub/ExplanationHardness