MolSC: Leveraging Substituent Contributions to Enhance Fine-grained Molecular Understanding in LLMs
The experiments show that existing molecular LLMs and strong proprietary models such as GPT-5.2 and Gemini-3-Flash show limited reliability in substituent contribution prediction, and training on MolSC substantially improves this ability and achieves strong performance across diverse downstream molecular tasks.
Hyuntae Park, Sooyeon Kim, J. Park et al.
· 0 citations