用图工具增强小模型，让其更准预测分子属性。
Improving Molecular Property Prediction in Small Language Models Using Graph-based Tools
- 引入图神经网络提供结构提示和解释子图。
- 在MUTAG和Tox21上提升超25%准确率，最高达74%。
- 适合想提升小模型分子预测能力的研究者。
小语言模型（SLMs）在从SMILES字符串进行零样本分子属性预测方面展现出潜力，但常因序列表示无法充分捕捉关键的图拓扑信息而存在结构盲区。我们提出一种模块化上下文增强提示框架，可在推理时实现代理式工具调用：训练好的GNN专家模型提供带置信度的预测提示，同时另一个GNN提取实例特定的解释性子图（如子图SMILES及配套解释段落）。我们在MUTAG和Tox21数据集上对三种常用SLMs进行了评估，采用从仅使用SMILES到融合所有可用工具的五种提示配置。在两个数据集上，加入图衍生上下文后，准确率显著提升，相对增益普遍超过25%，在Tox21上最高达74%。我们还通过基于必要性的边删除干预验证了提取基序的功能相关性。尽管取得显著进步，与专用GNN模型相比仍存在明显差距，凸显了文本条件推理在分子结构理解中的价值与局限。
原文摘要 · Abstract (English)
Small language models (SLMs) have shown promise for zero-shot molecular property prediction from SMILES strings, yet they often suffer from structural blindness because sequence representations under-specify key graph-topological cues. We propose a modular Context-Augmented Prompting framework that enables agentic tool use at inference time: a trained GNN expert model provides a predictive hint with confidence, and a GNN extracts an instance-specific explanatory subgraph (e.g., a subgraph SMILES and an accompanying explanatory paragraph). We evaluate three commonly used SLMs on MUTAG and Tox21 under five prompting configurations ranging from SMILES-only to using all available tools at hand. Across two datasets, enriching prompts with graph-derived context yields substantial accuracy gains, often exceeding 25% relative improvement and up to 74% on Tox21. We further validate the functional relevance of the extracted motifs via a necessity-based edge-drop intervention. Despite the observed gains, a persistent gap remains to specialized GNN models, highlighting both the value and limits of text-conditioned reasoning for molecular structure.
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。