Odor Maps from the LLM-derived similarity scores

TL;DR

This paper investigates how large language models can generate odor similarity maps, showing they can partially infer odor relationships and produce meaningful odor maps aligned with human perception.

Contribution

The study demonstrates that LLM-derived similarity scores can be used to create odor maps that reflect human odor perception and groupings.

Findings

LLMs can infer odor similarity to some extent.

Generated odor maps cluster similar odors and essential oils.

Proximity in the map correlates with human evaluation.

Abstract

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.