16 followers
AI that "explains itself" got studied. Turns out the explanations lie too. Shocking. https://doi.org/10.1007/s12599-026-01015-y #PRISCGroup #ainews
So far, Altmetric has seen
8 Bluesky posts from 2 Bluesky users, with an upper bound of 342 followers.
326 followers
harm. Attention to these caveats can help guide future research to improve the quality and impact of AI explanations. [6/6 of https://arxiv.org/abs/2504.06791v1]
326 followers
and even reduced AI adoption. Therefore, we caution stakeholders to beware of explanations of AI: while they can be vital, they are not automatically a remedy for transparency or responsible AI adoption, and their misuse or limitations can exacerbate [5…
326 followers
quality (e.g. unfaithful, irrelevant, or incoherent), potentially leading to substantial risks. Instead of fostering trust and safety, poorly designed explanations can actually cause harm, including wrong decisions, privacy violations, manipulation, [4/…