用语言模型自研化学规则，零微调预测分子属性，省时省钱。
Socrates-Mol: Self-Oriented Cognitive Reasoning through Autonomous Trial-and-Error with Empirical-Bayesian Screening for Molecules
- 让语言模型自己试错并结合实验数据迭代推理，生成可复用的化学规律。
- 在胺类溶剂LogP预测中，回归任务误差降72%，拟合度提升112%。
- 适合工业筛选场景，无需训练，部署成本降低超70%。
分子性质预测是化学工程应用（如溶剂筛选）的基础。我们提出Socrates-Mol框架，通过上下文设计将语言模型转化为经验贝叶斯推理器，无需模型微调即可解决冷启动问题。系统采用反思-预测循环：初始输出作为先验，检索到的分子案例提供证据，优化后的预测形成后验，并从稀疏数据中提取可复用的化学规则。引入与工业筛选优先级对齐的排序任务，利用五种语言模型间的自一致性来降低方差。在胺类溶剂LogP预测实验中显示：回归任务实现72%的平均绝对误差降低和112%的决定系数提升；而排序任务增益有限，因存在系统性多模型偏差。该框架相比全量微调降低部署成本超70%，为分子性质预测提供可扩展方案，同时揭示了自一致性机制的任务适应性。
原文摘要 · Abstract (English)
Molecular property prediction is fundamental to chemical engineering applications such as solvent screening. We present Socrates-Mol, a framework that transforms language models into empirical Bayesian reasoners through context engineering, addressing cold start problems without model fine-tuning. The system implements a reflective-prediction cycle where initial outputs serve as priors, retrieved molecular cases provide evidence, and refined predictions form posteriors, extracting reusable chemical rules from sparse data. We introduce ranking tasks aligned with industrial screening priorities and employ cross-model self-consistency across five language models to reduce variance. Experiments on amine solvent LogP prediction reveal task-dependent patterns: regression achieves 72% MAE reduction and 112% R-squared improvement through self-consistency, while ranking tasks show limited gains due to systematic multi-model biases. The framework reduces deployment costs by over 70% compared to full fine-tuning, providing a scalable solution for molecular property prediction while elucidating the task-adaptive nature of self-consistency mechanisms.
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。