MolReasoner: Toward Effective and Interpretable Reasoning for Molecular LLMs
This work addresses the challenge of enhancing domain-specific reasoning for molecular LLMs, representing an incremental improvement over current fine-tuning and prompting approaches.
The paper tackles the problem of insufficient molecular reasoning in Large Language Models (LLMs) by introducing MolReasoner, a two-stage framework that shifts LLMs from memorization to chemical reasoning, resulting in improved interpretability and outperforming existing methods.
Large Language Models(LLMs) have demonstrated remarkable performance across various domains, yet their capabilities in molecular reasoning remain insufficiently explored. Current approaches tend to rely heavily on general-purpose prompting, which lacks domain-specific molecular semantics, while those that use fine-tuning strategies often face challenges with interpretability and reasoning depth. To address these issues, we introduce MolReasoner, a two-stage framework designed to transition LLMs from memorization towards chemical reasoning. First, we propose Mol-SFT, which initializes the model's reasoning abilities via synthetic Chain-of-Thought(CoT) samples generated by GPT-4o and verified for chemical accuracy. Subsequently, Mol-RL applies reinforcement learning with specialized reward functions designed explicitly to align chemical structures with linguistic descriptions, thereby enhancing molecular reasoning capabilities. Our approach notably enhances interpretability, improving the model 's molecular understanding and enabling better generalization. Extensive experiments demonstrate that MolReasoner outperforms existing methods, and marking a significant shift from memorization-based outputs to robust chemical reasoning.