Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.20310 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914498357493760 |
|---|---|
| author | Harada, Yuki Aleixandre, Manuel Okumura, Manabu Nakamoto, Takamichi |
| author_facet | Harada, Yuki Aleixandre, Manuel Okumura, Manabu Nakamoto, Takamichi |
| contents | The application of large language models (LLMs) to OdorSpace analysis attracts growing interest. Recent studies have explored the comparison of sensory evaluation spaces derived from LLMs with odor character profiles in the Dravnieks' dataset. In this study, we calculated pairwise distances of odor descriptors using three distance measures and statistically compared these LLM-derived similarities with distances derived from the original data. Next, we extended this approach to odor names (ingredients). Statistical comparison revealed that LLMs can infer odor similarity to some degree, suggesting the potential of odor maps generated from these similarity data. Applying this approach, we generated an odor map of essential oils. It demonstrates that essential oils within the same group are closely located in the odor map, suggesting that the proximity in the odor map corresponds to human evaluation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_20310 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Odor Maps from the LLM-derived similarity scores Harada, Yuki Aleixandre, Manuel Okumura, Manabu Nakamoto, Takamichi Human-Computer Interaction The application of large language models (LLMs) to OdorSpace analysis attracts growing interest. Recent studies have explored the comparison of sensory evaluation spaces derived from LLMs with odor character profiles in the Dravnieks' dataset. In this study, we calculated pairwise distances of odor descriptors using three distance measures and statistically compared these LLM-derived similarities with distances derived from the original data. Next, we extended this approach to odor names (ingredients). Statistical comparison revealed that LLMs can infer odor similarity to some degree, suggesting the potential of odor maps generated from these similarity data. Applying this approach, we generated an odor map of essential oils. It demonstrates that essential oils within the same group are closely located in the odor map, suggesting that the proximity in the odor map corresponds to human evaluation. |
| title | Odor Maps from the LLM-derived similarity scores |
| topic | Human-Computer Interaction |
| url | https://arxiv.org/abs/2604.20310 |