Evaluating In‐Context Learning in Large Language Models for Molecular Property Regression
Abstract
Large language models (LLMs) demonstrate strong performance in natural language tasks, but their capacity for genuine in-context learning (ICL) in scientific regression remains unclear. We systematically assessed seven LLMs on molecular property prediction using a controlled framework of 56 transformed tasks that isolate shortcut learning and are designed to induce functional out-of-distribution (OOD) behavior. LLMs performed nearly perfectly on raw molecular weight prediction via shortcut cues but deteriorated under nonlinear transformations, whereas machine learning (ML) baselines showed greater robustness, yielding a performance crossover. Meta-analysis revealed that distributional descriptors and structure-activity landscape indices (SALI) predict task favorability, providing a framework for selecting between LLM- and ML-based approaches in chemistry.
Fields of Study & Subjects
Machine Learning in Materials Science
Computational Drug Discovery Methods
Advanced Graph Neural Networks
Publication details
- Journal / source
- Journal of Computational Chemistry
- Publisher
- Wiley
- Volume
- 47
- Issue
- 2
- Pages
- e70308–e70308
- Publication date
- 15 January 2026
- Language
- EN