From Competition to Collaborative Smelling: Navigating the Olfactory Gap in Human-AI Interaction

Addressing the olfactory-verbal gap remains a key challenge in Human-Computer Interaction (HCI), as the subjective nature of smell often resists precise articulation. We introduce Smell with Genji, an Artificial Intelligence (AI)-mediated olfactory experience that adapts the traditional Japanese olfactory game Genji-kō into a research probe for structured comparison and articulation. Through an iterative development process, we describe a shift from a Competition Model, where AI benchmarks alignment with human judgments, to a Partnership Model, where AI functions as a co-smelling partner during iterative comparison. Leveraging Large Language Models (LLMs), the system transforms sensing latency into dialogic engagement within the interactional flow. Preliminary findings from two pilot studies (n = 16) suggest that the system facilitates novice users in organizing and articulating comparative scent judgments through data-informed interaction. Our work proposes that beyond technical precision, the value of olfactory AI can be found in its role as a collaborative partner within structured sensory comparison.