Sniff AI: Is My 'Spicy' Your 'Spicy'? Exploring LLM's Perceptual Alignment with Human Smell Experiences
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912113638768640 |
|---|---|
| author | Zhong, Shu Zhou, Zetao Dawes, Christopher Brianz, Giada Obrist, Marianna |
| author_facet | Zhong, Shu Zhou, Zetao Dawes, Christopher Brianz, Giada Obrist, Marianna |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_06950 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Sniff AI: Is My 'Spicy' Your 'Spicy'? Exploring LLM's Perceptual Alignment with Human Smell Experiences Zhong, Shu Zhou, Zetao Dawes, Christopher Brianz, Giada Obrist, Marianna Computation and Language Human-Computer Interaction 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. |
| title | Sniff AI: Is My 'Spicy' Your 'Spicy'? Exploring LLM's Perceptual Alignment with Human Smell Experiences |
| topic | Computation and Language Human-Computer Interaction |
| url | https://arxiv.org/abs/2411.06950 |