Papers with Mistral Large 2
Molecular String Representation Preferences in Pretrained LLMs: A Comparative Study in Zero- & Few-Shot Molecular Property Prediction (2025.emnlp-main)
Copied to clipboard
| Challenge: | Molecular property prediction plays a crucial role in medicinal chemistry . traditional machine learning approaches do not involve natural language . |
| Approach: | They compare performance of four state-of-the-art LLMs on molecular property prediction tasks . they find statistically significant zero- and few-shot preferences for InChI and IUPAC names . |
| Outcome: | The proposed model outperforms the current model on molecular property prediction tasks . the model's representation preferences are based on representation granularity, tokenization and prevalence in pretraining corpora . |