让大模型真正懂化学机理,通过原子级知识提升推理能力
ChemDFM-R: A Chemical Reasoning LLM Enhanced with Atomized Chemical Knowledge
- 构建分子功能团数据集ChemFG,注入原子级化学知识
- 四阶段训练使模型在多个基准上超越主流化学LLM
- 输出可解释的推理链,适合科研协作与工业应用
原子级化学知识(如分子中的官能团及其反应变化)在连接分子结构与性质、反应活性的推理过程中起关键作用。尽管大语言模型进展显著,但缺乏此类知识导致其对化学的理解浅层且推理能力受限。为此,我们提出化学推理大模型ChemDFM-R。首先构建涵盖分子官能团及反应中官能团演变的综合数据集ChemFG,增强模型对化学基本原理和内在逻辑的理解。接着提出混合源蒸馏方法,以少量蒸馏数据初始化推理能力,并设计四阶段训练流程,使模型掌握原子级化学知识与推理逻辑。在多种化学基准上的实验表明,ChemDFM-R达到顶尖性能,输出可解释、基于理由的推理结果,优于通用与专用化学大模型。此外,其表现媲美甚至超过o4-mini等先进商用模型。案例研究显示,显式推理链显著提升模型在人机协作场景下的可靠性、透明性与实用性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。