MolReasoner: Toward Effective and Interpretable Reasoning for Molecular LLMs
Abstract
MolReasoner, a two-stage framework, enhances LLMs for molecular reasoning through synthetic Chain-of-Thought samples and reinforcement learning with specialized reward functions, improving interpretability and generalization.
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.
Community
Hi everyone,
We are excited to introduce our paper MolReasoner. We hope that MolReasoner will not only serve as a strong baseline model but also inspire further exploration in the field of molecular LLMs, driving the emergence of new ideas, benchmarks, and open-source collaborations, all aimed at achieving truly autonomous chemical reasoning. To support the progress of the research community, we have open-sourced the reproducible code and provided evaluation scripts consistent with the paper. For more details, please visit: https://github.com/545487677/MolReasoner
Models citing this paper 1
Datasets citing this paper 1
Spaces citing this paper 0
No Space linking this paper
Collections including this paper 0
No Collection including this paper