LoRA让大模型高效学习化学反应，避免遗忘旧知识。
Modular Multi-Task Learning for Chemical Reaction Prediction
- 用低秩适配（LoRA）替代全量微调，节省参数。
- 在复杂反应预测任务中，精度接近全微调，且抗灾难性遗忘。
- 适合需要快速部署、多任务并行的化学研发场景。
将广泛训练的大语言模型（LLMs）应用于小规模、特定领域的有机化学反应数据集，是化学与制药研发中的关键挑战。有效专业化需在学习新反应知识的同时保留跨相关任务的通用化学理解。本文评估了低秩适配（LoRA）作为全量微调的参数高效替代方案，在有限且复杂的反应数据集上的表现。基于美国专利局（USPTO）反应类别及具有挑战性的C-H官能团化反应，我们对正向反应预测、逆合成分析和试剂预测进行了基准测试。结果表明，LoRA在准确率上与全微调相当，同时有效缓解了灾难性遗忘，并更好保持了多任务性能。两种微调方法均能泛化至训练分布之外，生成合理的溶剂预测。值得注意的是，针对C-H官能团化的微调显示，LoRA与全微调编码了略有不同的反应活性模式，暗示LoRA可能实现更有效的反应特异性适应。随着大模型持续扩展，本研究凸显了模块化、参数高效的微调策略在化学应用中灵活部署的可行性。
原文摘要 · Abstract (English)
Adapting large language models (LLMs) trained on broad organic chemistry to smaller, domain-specific reaction datasets is a key challenge in chemical and pharmaceutical R&D. Effective specialisation requires learning new reaction knowledge while preserving general chemical understanding across related tasks. Here, we evaluate Low-Rank Adaptation (LoRA) as a parameter-efficient alternative to full fine-tuning for organic reaction prediction on limited, complex datasets. Using USPTO reaction classes and challenging C-H functionalisation reactions, we benchmark forward reaction prediction, retrosynthesis and reagent prediction. LoRA achieves accuracy comparable to full fine-tuning while effectively mitigating catastrophic forgetting and better preserving multi-task performance. Both fine-tuning approaches generalise beyond training distributions, producing plausible alternative solvent predictions. Notably, C-H functionalisation fine-tuning reveals that LoRA and full fine-tuning encode subtly different reactivity patterns, suggesting more effective reaction-specific adaptation with LoRA. As LLMs continue to scale, our results highlight the practicality of modular, parameter-efficient fine-tuning strategies for their flexible deployment for chemistry applications.
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。