MolGround: A Benchmark for Molecular Grounding
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909597928783872 |
|---|---|
| author | Wu, Jiaxin Zhang, Ting Chen, Rubing Zhang, Wengyu Zhang, Chen Jason Wei, Xiao-Yong Qing, Li |
| author_facet | Wu, Jiaxin Zhang, Ting Chen, Rubing Zhang, Wengyu Zhang, Chen Jason Wei, Xiao-Yong Qing, Li |
| contents | Current molecular understanding approaches predominantly focus on the descriptive aspect of human perception, providing broad, topic-level insights. However, the referential aspect -- linking molecular concepts to specific structural components -- remains largely unexplored. To address this gap, we propose a molecular grounding benchmark designed to evaluate a model's referential abilities. We align molecular grounding with established conventions in NLP, cheminformatics, and molecular science, showcasing the potential of NLP techniques to advance molecular understanding within the AI for Science movement. Furthermore, we constructed the largest molecular understanding benchmark to date, comprising 117k QA pairs, and developed a multi-agent grounding prototype as proof of concept. This system outperforms existing models, including GPT-4o, and its grounding outputs have been integrated to enhance traditional tasks such as molecular captioning and ATC (Anatomical, Therapeutic, Chemical) classification. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_23668 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MolGround: A Benchmark for Molecular Grounding Wu, Jiaxin Zhang, Ting Chen, Rubing Zhang, Wengyu Zhang, Chen Jason Wei, Xiao-Yong Qing, Li Artificial Intelligence Current molecular understanding approaches predominantly focus on the descriptive aspect of human perception, providing broad, topic-level insights. However, the referential aspect -- linking molecular concepts to specific structural components -- remains largely unexplored. To address this gap, we propose a molecular grounding benchmark designed to evaluate a model's referential abilities. We align molecular grounding with established conventions in NLP, cheminformatics, and molecular science, showcasing the potential of NLP techniques to advance molecular understanding within the AI for Science movement. Furthermore, we constructed the largest molecular understanding benchmark to date, comprising 117k QA pairs, and developed a multi-agent grounding prototype as proof of concept. This system outperforms existing models, including GPT-4o, and its grounding outputs have been integrated to enhance traditional tasks such as molecular captioning and ATC (Anatomical, Therapeutic, Chemical) classification. |
| title | MolGround: A Benchmark for Molecular Grounding |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2503.23668 |