Sniff AI: Is My 'Spicy' Your 'Spicy'? Exploring LLM's Perceptual Alignment with Human Smell Experiences
Aligning AI with human intent is important, yet perceptual alignment-how AI interprets what we see, hear, or smell-remains underexplored. This work focuses on olfaction, human smell experiences. We conducted a user study with 40 participants to investigate how well AI can interpret human descriptions of scents. Participants performed "sniff and describe" interactive tasks, with our designed AI system attempting to guess what scent the participants were experiencing based on their descriptions. These tasks evaluated the Large Language Model's (LLMs) contextual understanding and representation of scent relationships within its internal states - high-dimensional embedding space. Both quantitative and qualitative methods were used to evaluate the AI system's performance. Results indicated limited perceptual alignment, with biases towards certain scents, like lemon and peppermint, and continued failing to identify others, like rosemary. We discuss these findings in light of human-AI alignment advancements, highlighting the limitations and opportunities for enhancing HCI systems with multisensory experience integration.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
How do non-tastes taste? A corpus-based study on Chinese people’s perception of spicy and numbing food
Will releasing the weights of future large language models grant widespread access to pandemic agents?
Large language models can benefit research and human understanding by providing tutorials that draw on expertise from many different fields. A properly safeguarded model will refuse to provide "dual-use" insights that co…
Spicy Salmon: Converting between 50+ Annotation Formats with Fintan, Pepper, Salt and Powla
Heterogeneity of formats, models and annotations has always been a primary hindrance for exploiting the ever increasing amount of existing linguistic resources for real world applications in and beyond NLP. Fintan - the …
RuleWeaver: Benchmarking Rule-Centered Scenario Reasoning for Large Language Models
Large language models (LLMs) are increasingly applied to specialized domains, where effective use of domain expertise often requires reasoning over complex rules in concrete scenarios. However, existing benchmarks only p…
Exploring Dual-Sniffer Passive Localization: Algorithm Design and Experimental Results
In this paper, we explore a dual-sniffer passive localization system that detects the timing difference of signals from both commercial base station (eNb) and user equipment (UE) to the sniffers. We design two localizati…
Position