ChemDFM-R: A Chemical Reasoning LLM Enhanced with Atomized Chemical Knowledge

TL;DR

ChemDFM-R is a novel chemical reasoning LLM enhanced with atomized chemical knowledge, improving interpretability, reasoning, and performance on chemical tasks compared to existing models.

Contribution

The paper introduces ChemDFM-R, a chemical reasoning LLM trained with a new atomized chemical knowledge dataset and a four-stage training pipeline, advancing chemical AI capabilities.

Findings

Achieves state-of-the-art performance on chemical benchmarks.

Provides interpretable, rationale-driven outputs.

Outperforms both general and domain-specific LLMs.

Abstract

Atomized chemical knowledge, such as functional group information of molecules and reactions, plays a pivotal intermediate role in the reasoning process that connects molecular structures with their properties and reactivities. While large language models (LLMs) have achieved impressive progress, the absence of atomized chemical knowledge results in their superficial understanding of chemistry and limited chemical reasoning capabilities. In this work, to tackle this problem, we develop a Chemical Reasoning LLM, ChemDFM-R. We first construct a comprehensive dataset of atomized chemical knowledge, ChemFG, annotating the presence of functional groups in molecules and the changes of functional groups during chemical reactions, to enhance the model's understanding of the fundamental principles and internal logic of chemistry. Then, we propose a mixed-source distillation method that initializes the model's reasoning capability with limited distilled data, and develop a four-stage training pipeline to equip the model with atomized chemical knowledge and chemical reasoning logic. Experiments on diverse chemical benchmarks demonstrate that ChemDFM-R achieves cutting-edge performance while providing interpretable, rationale-driven outputs, surpassing both the general-domain LLMs and domain-specific chemical LLMs. Moreover, ChemDFM-R achieves comparable or superior performance compared with cutting-edge commercial LLMs, such as o4-mini. Further case studies illustrate how explicit reasoning chains significantly improve the model's reliability, transparency, and practicality in real-world human-AI collaboration scenarios.