Metraipolis › archive › dc_248a4e394135
General-purpose foundation models surpass specialized ones on chemical property prediction tasks — arXiv:2610.41899
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.41899
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T07:43:28.193Z
- SHA-256 of the archived text
ad7ea3846810b4579ae2635ad98a117ece7d86f25fa36bee3f483f313f6915ed- Stable URL of this page
https://metraipolis.com/documento/dc_248a4e394135
How to cite
General-purpose foundation models surpass specialized ones on chemical property prediction tasks — arXiv:2610.41899 — arXiv (en), https://arxiv.org/abs/2610.41899 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_248a4e394135 (Metraipolis archive dc_248a4e394135, sha256 ad7ea3846810b4579ae2635ad98a117ece7d86f25fa36bee3f483f313f6915ed)
BibTeX
@misc{dc248a4e394135,
title = {General-purpose foundation models surpass specialized ones on chemical property prediction tasks — arXiv:2610.41899},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.41899},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_248a4e394135; sha256 ad7ea3846810b4579ae2635ad98a117ece7d86f25fa36bee3f483f313f6915ed},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41899. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Foundation models (FMs) learn reusable representations from large collections of unlabeled data. In chemistry the corresponding data mainly consists of molecular structures, which are abundant, whereas experimental measurements are scarce. Chemical FMs such as ChemBERTa and MoLFormer were therefore trained on diverse molecular structures to enable fine-tuning on small experimental datasets (less than 100 datapoints in most realistic scenarios) and subsequent property prediction. At the same time, general-purpose FMs such as GPT-6 Astra and Claude Opus 5.5 were trained on virtually all publicly available data, including knowledge of the humankind on molecular properties and laws governing them. Here we compare accuracies of chemical and general-purpose FMs on tasks from various areas of chemistry. Strikingly, general-purpose GPT-6 Astra outperforms the currently eligible chemical FMs on five physicochemical and quantum-chemical regression tasks when only 60 experimental datapoints are available. Only when provided 10x datapoints do the best chemical FMs reach performance of GPT-6 Astra: on 1,000 and 10,000 points they show performance on par with Astra on 60 and 1,000 points, respectively. Thus, counterintuitively, frontier general-purpose FMs are better suited for guiding chemical research in data-scarce areas than specialized chemical FMs, suggesting that learning relevant primitives (e.g. chemical structures) does not substitute training on relevant humankind knowledge. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Chemical Physics (physics.chem-ph) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.41899 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-03T07:39:37.399Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).