通过微调增强推理能力的大语言模型以桥接化学合成与发现中的可信度-有效性鸿沟

Large Language Models frequently generate outputs that appear scientifically reasonable yet violate fundamental principles--a phenomenon we characterize as the "plausibility-validity gap." This challenge proves especially acute in chemistry, where superficial correctness masks deeper errors in molecular structure, reaction mechanisms, and synthetic pathways. We present a systematic approach combining a reasoning-centric model architecture (Magistral Small) with Low-Rank Adaptation fine-tuning on a dual-domain dataset covering molecular properties and chemical transformations. Evaluation reveals substantial improvements: the fine-tuned system achieves 96.3% format adherence, 97.4% chemical validity, and 74.4% synthesis feasibility. Comparative analysis shows our approach outperforms specialized translation models like MolT5 (97.4% vs 77.2% validity) while achieving performance comparable to complex tool-augmented systems like ChemCrow (9.0/10 vs 9.24/10 expert rating) through a more transparent, efficient methodology. Results demonstrate a learning hierarchy where syntactic correctness develops before chemical understanding, which precedes synthetic planning capability. This work establishes a reproducible framework for transforming generalist language models into dependable scientific tools while identifying critical areas including stereochemical precision, knowledge currency, and computational accessibility as key challenges for future advancement. 大语言模型经常生成表面上看起来合理却违反基本原理的输出——我们将这种现象称为 "可信度-有效性鸿沟"。这一挑战在化学领域尤为突出，由于表面正确性掩盖了分子结构、反应机制和合成路径方面的深层错误。我们提出了一种系统性方法，将以推理为中心的模型架构 (Magistral Small) 与针对覆盖分子属性和化学变换的双域数据集进行 Low-Rank Adaptation 微调。评估结果显示，微调后的系统实现了 96.3% 的格式遵循率、97.4% 的化学有效性以及 74.4% 的合成可行性。比较分析表明，我们的方法优于像 MolT5 这类专业化翻译模型（97.4% vs 77.2% 有效性），同时通过更透明、更高效的方法实现了与复杂工具增强系统如 ChemCrow（9.0/10 vs 9.24/10 专家评分）相当的性能。结果显示，语法正确性在化学理解之前发展，化学理解又在合成规划能力之前出现。这项工作为将通用语言模型转化为可靠的科学工具建立了可复现的框架，同时识别出包括立体化学精度、知识时效性和计算可达性等关键挑战作为未来发展的关键领域。