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 the darkness of the deep sea, there are all sorts of strange activities that have never before been seen by human eyes. With a lifeless gaze, a dangling bioluminescent protrusion that juts from their face, and a gaping mouth filled with razor-sharp teeth, anglerfish may be among the best representations of the peculiarities thousands of feet beneath the surface. And, their mating habits are fittingly bizarre. Anglerfish engage in what's known as sexual parasitism; the male latches onto the female and slowly fuses with her body until the two have formed a permanent pair, with the male supplying sperm to his mate while simultaneously receiving nutrients. Now, in what's said to be a'rare and important' discovery, scientists have captured footage of live anglerfish mating for the first time, according to an exclusive report in Science Magazine.