Mascart, Cyrille, Tran, Khue, Samoilova, Khristina, Storan, Liam Thomas, Liu, Tingkai, Koulakov, Alexei (March 2026) Grounding olfactory perception in language: Benchmarks and models for generating natural language odor descriptions. bioRxiv. ISSN 2692-8205 (Submitted)
![[thumbnail of 10.64898.2026.03.04.709650.pdf]](https://repository.cshl.edu/style/images/fileicons/application_pdf.png) |
PDF
10.64898.2026.03.04.709650.pdf - Submitted Version Available under License Creative Commons Attribution. Download (2MB) |
Abstract
Recent advances in deep learning have enabled prediction of odorant perception from molecular structure, opening new avenues for odor classification. However, most existing models are limited to predicting percepts from fixed vocabularies and fail to capture the full richness of olfactory experience. Progress is further limited by the scarcity of large-scale olfactory datasets and the lack of standardized metrics for evaluating free-form natural-language odor descriptions. To address these challenges, we introduce Odor Description and Inference Evaluation Understudy (ODIEU), a benchmark which includes perceptual descriptions of over 10,000 molecules paired with a model-based metric for evaluating free-form odor text descriptions. The model-based metric uses Sentence-BERT (SBERT) models which are fine-tuned on olfactory descriptions to allow better evaluation of human-generated odor texts. Using the fine-tuned SBERT models, we show that free-form text odor descriptions contain additional perceptual information in their syntactic structure compared to semantic labels. We further introduce CIRANO (Chemical Information Recognition and Annotation Network for Odors), a transformer-based model that generates free-form odor descriptions directly from molecular structure, thus implementing the molecular structure-to-text (S2T) prediction. CIRANO achieves performance comparable to humans. Finally, we generate human-like descriptions from mouse olfactory bulb neural data using an invertible SBERT model, yielding neural-to-text (N2T) predictions highly aligned with human descriptions. Together, CIRANO and ODIEU establish a standardized framework for generating natural language olfactory descriptions and evaluating their alignment with human perception. Code is available at https://github.com/KoulakovLab/ODIEU.
| Item Type: | Paper |
|---|---|
| Subjects: | bioinformatics organism description > animal behavior organism description > animal behavior > olfactory |
| CSHL Authors: | |
| Communities: | CSHL Post Doctoral Fellows CSHL labs > Koulakov lab |
| SWORD Depositor: | CSHL Elements |
| Depositing User: | CSHL Elements |
| Date: | 5 March 2026 |
| Date Deposited: | 29 Jun 2026 13:32 |
| Last Modified: | 29 Jun 2026 13:32 |
| PMCID: | PMC13001309 |
| Related URLs: | |
| URI: | https://repository.cshl.edu/id/eprint/42151 |
Actions (login required)
 |
Administrator's edit/view item |