ChemDFM-R：一种融合原子化化学知识的化学推理大语言模型

摘要

儘管大型語言模型（LLMs）已取得顯著進展，其在化學等科學領域的應用仍受制於淺薄的領域理解與有限的推理能力。本研究聚焦於化學這一特定領域，開發了一款化學推理大型語言模型——ChemDFM-R。首先，我們構建了一個全面的原子化知識點數據集，以增強模型對化學基本原理與邏輯結構的理解。隨後，提出了一種混合來源的蒸餾策略，將專家精選的知識與通用領域的推理技能相結合，並通過領域特定的強化學習來提升化學推理能力。在多樣化的化學基準測試中，ChemDFM-R展現了頂尖的性能，同時提供了可解釋、基於推理的輸出結果。進一步的案例研究表明，明確的推理鏈顯著提升了模型在實際人機協作場景中的可靠性、透明度及實用性。

English

While large language models (LLMs) have achieved impressive progress, their application in scientific domains such as chemistry remains hindered by shallow domain understanding and limited reasoning capabilities. In this work, we focus on the specific field of chemistry and develop a Chemical Reasoner LLM, ChemDFM-R. We first construct a comprehensive dataset of atomized knowledge points to enhance the model's understanding of the fundamental principles and logical structure of chemistry. Then, we propose a mix-sourced distillation strategy that integrates expert-curated knowledge with general-domain reasoning skills, followed by domain-specific reinforcement learning to enhance chemical reasoning. Experiments on diverse chemical benchmarks demonstrate that ChemDFM-R achieves state-of-the-art performance while providing interpretable, rationale-driven outputs. Further case studies illustrate how explicit reasoning chains significantly improve the reliability, transparency, and practical utility of the model in real-world human-AI collaboration scenarios.

ChemDFM-R：一种融合原子化化学知识的化学推理大语言模型

ChemDFM-R: An Chemical Reasoner LLM Enhanced with Atomized Chemical Knowledge

摘要

Support