arXiv：cs.AI· Farhad Pashakhanloo, Venkatesh N. Murthy·· 6 小时前
用 LLM 派生描述学习自然气味混合物的感知几何
Learning Perceptual Geometry of Natural Odor Mixtures from LLM-Derived Descriptors
AI 导读
研究利用 LLM 为含 8000 多个分子组分的 1200 多种食物挥发物混合物生成感知描述，并据此从分子组成预测留出混合物的相似度，效果在采用化学感知提示词时最强。训练中学到的低秩分子嵌入在预测留出混合物相似度上优于组分重叠指标，即使混合物对之间没有共享分子，且其分子几何与独立的人类气味描述符空间显著对齐。外部分子特征仅在有限监督下改善预测，使用完整训练集时增益有限。
正文
Abstract:The relationship between odor chemistry and perception remains incompletely understood. Many existing studies focus on the perception of single molecules, whereas natural odors contain tens to hundreds of components, adding extra layer of complexity to percept formation. Here, we explore the relationship between molecular composition and perceived similarity in natural odor objects. We study this using a database of more than 1,200 volatile-compound-in-food mixtures containing more than 8,000 molecular components, and use large language models (LLMs) as a scalable surrogate for deriving mixture-level perceptual descriptions. We find that language-derived representations provide useful supervision for predicting held-out mixture similarities from molecular composition. The prediction was consistently strongest when perceptual targets were derived from chemosensory prompts than from other sensory prompts. Further, during the mixture-level training, we learned low-rank molecular embeddings that enabled better prediction of held-out mixture similarities than component-overlap metrics, even for mixture pairs with no shared molecules. Although no single-molecule labels were used during training, the learned molecular geometry showed significant alignment with the independent human odor-descriptor space. Finally, we explored the use of external molecular features in our mixture-similarity prediction task. These features showed modest zero-shot alignment with mixture-level perceptual similarity. They improved prediction under limited supervision but offered little additional predictive benefit with the full training set. Together, these results show that language-derived descriptions can provide scalable supervision for predicting the perceptual organization of complex natural mixtures, contributing to a quantitative understanding of how molecular composition gives rise to odor perception.
| Comments: | 26 pages, 14 figures |
| Subjects: | Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Neurons and Cognition (q-bio.NC) |
| Cite as: | arXiv:2610.17164 [cs.AI] |
| (or arXiv:2610.17164v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.17164 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Farhad Pashakhanloo [view email]
[v1]
Mon, 12 Oct 2026 17:41:14 UTC (3,400 KB)
来源：arXiv：cs.AI · arxiv.org