面向单步逆合成的化学合理性感知大语言模型训练
Training Chemical Plausibility-Aware Large Language Models for Single-Step Retrosynthesis
浏览论文内容
中文总结 AI 辅助
该研究针对单步逆合成的一对多特性，提出Top-K提示范式，构建超大规模反应数据集训练C3LM，结合特定奖励机制在基准上达最优性能，为逆合成系统提供新方向。
中文摘要 AI 辅助
单步逆合成是计算机辅助合成规划的核心组成部分，但其内在的一对多特性难以被单答案评估与基准测试协议充分捕捉。为解决该问题，我们引入Top-K提示作为稳健的训练与推理范式，以更好地捕捉多样且合理的反应预测结果。我们构建了CREED-CCV-2+USPTO-XL，这一包含约4560万条验证反应的超大规模数据集，用于训练C3LM（化学约束一致语言模型）。通过将微调与基于ChemCensor的奖励及面向新颖性的奖励相结合，我们的模型在OOD URSA-expert-2026基准上实现了最先进的性能。对反应唯一性的进一步分析显示，大语言模型与传统模型探索互补的反应空间，这为基于集成的逆合成系统提供了动力。总体而言，我们的研究结果确立了Top-K、合理性感知训练这一方向，为未来基于大语言模型的稳健合成规划提供了实用的新路径。
英文摘要
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.
发表机构
- Insilico Medicine AI Limited（英矽智能人工智能有限公司）
- Insilico Medicine Canada Inc.（英矽智能加拿大公司）
- Insilico Medicine Hong Kong Ltd.（英矽智能香港有限公司）
机构由 AI 辅助整理，请以论文原文为准。
