An important factor when it comes to generating fact-checking explanations is the selection of evidence: intuitively, high-quality explanations can only be generated given the right evidence. In this work, we investigate the impact of human-curated vs. machine-selected evidence for explanation generation using large language models. To assess the quality of explanations, we focus on transparency (whether an explanation cites sources properly) and utility (whether an explanation is helpful in clarifying a claim). Surprisingly, we found that large language models generate similar or higher quality explanations using machine-selected evidence, suggesting carefully curated evidence (by humans) may not be necessary. That said, even with the best model, the generated explanations are not always faithful to the sources, suggesting further room for improvement in explanation generation for fact-checking.

In what is believed to be a world first, the A-Leagues have rolled out new software which uses machine-learning technology to stop any abusive …

Two teenage boys, struggling to make their way back to shore, were saved by a drone in Australia on Wednesday, in what officials say is a first-of-its-kind rescue mission by an unmanned aircraft -- one captured by the drone's camera and later broadcast by Arab News and other outlets. A beachgoer caught a glimpse of the distressed swimmers, 15 and 17, who were fighting dangerous waves off Australia's Far North Coast in New South Wales. He alerted lifeguards, who happened to be in the middle of a drone training session, learning how the unmanned aerial vehicles (UAV) work. Lifeguard supervisor Jai Sheridan got the call and piloted the drone, dubbed "Little Ripper," toward the swimmers, about 2,300 feet over the ocean. Within 70 seconds the drone was hovering over the boys and had dropped a self-inflating rescue pod into the water.