Artificial Dreams: Surreal Visual Storytelling as Inquiry Into AI ‘Hallucination’

Abstract

What does it mean for stochastic artifcial intelligence (AI) to “hallucinate” when performing a literary task as open-ended as creative visual storytelling? In this paper, we investigate AI “hallucination” by stress-testing a visual storytelling algorithm with diferent visual and textual inputs designed to probe dream logic inspired by cinematic surrealism. Following a close reading of 100 visual stories that we deem artifcial dreams, we describe how AI “hallucination” in computational visual storytelling is the opposite of groundedness: literary expression that is ungrounded in the visual or textual inputs. We fnd that this lack of grounding can be a source of either creativity or harm entangled with bias and illusion. In turn, we disentangle these obscurities and discuss steps toward addressing the perils while harnessing the potentials for innocuous cases of AI “hallucination” to enhance the creativity of visual storytelling.