训练化学合理性感知的大型语言模型用于单步逆合成

摘要

单步逆合成是计算机辅助合成规划的核心组成部分，然而其固有的“一对多”特性在单一答案评估与基准测试协议中难以得到充分体现。为解决这一问题，我们引入Top-K提示作为一种稳健的训练与推理范式，以更好地捕捉多样化且合理的反应预测。我们构建了CREED-CCV-2+USPTO-XL，一个包含约4560万个已验证反应的超大规模数据集，用于训练C3LM（化学约束一致性语言模型）。通过将基于ChemCensor的微调与面向新颖性的奖励相结合，我们的模型在OOD URSA-expert-2026基准上取得了最先进的性能。对反应独特性的进一步分析表明，大语言模型与传统模型探索了互补的反应空间，这为基于集成的逆合成系统提供了依据。总体而言，我们的研究结果确立了Top-K、合理性感知训练作为未来基于LLM的稳健合成规划的一个实用新方向。

English

Single-step retrosynthesis is a central component of computer-aided synthesis planning, yet its intrinsically one-to-many nature is poorly captured by single-answer evaluation and benchmarking protocols. To address this, we introduce Top-K prompting as a robust training and inference paradigm to better capture diverse, plausible reaction predictions. We compile CREED-CCV-2+USPTO-XL, an ultra-large-scale dataset of ~45.6 million verified reactions to train the C3LM (Chemistry Constraint-Consistent Language Model). By integrating fine-tuning with ChemCensor-based and novelty-oriented rewards, our model achieves state-of-the-art performance on the OOD URSA-expert-2026 benchmark. Further analysis of reaction uniqueness shows that LLMs and conventional models explore complementary reaction spaces, motivating ensemble-based retrosynthesis systems. Overall, our results establish Top-K, plausibility-aware training as a practical new direction for robust future LLM-based synthesis planning.