用溯源信息提升材料合成路径推理准确率
ProvMind: Provenance-grounded reasoning for materials synthesis
- 基于文献挖掘的合成溯源图构建评估基准，支持多任务测试
- 在严格双分布外场景下达到52.84%准确率，优于多种基线方法
- 适合材料科学与AI交叉研究者，尤其关注过程推理与可解释性
材料工艺优化需要对合成路径、条件、工具及因果关系进行推理，但现有计算方法常将合成流程简化为文本或顺序步骤。我们构建了MatProcBench，一个基于文献挖掘的MatPROV图谱的溯源基准，用于评估七种过程推理任务，涵盖路径连续性、步骤级变量推断和全局因果一致性，支持同分割与迁移感知评估，包括结合时间与材料类别漂移的严格双分布外（dual-OOD）划分。我们进一步提出ProvMind，一种过程记忆推理框架，通过检索相似训练过程，转化为溯源感知的选项级兼容性得分，并利用语言模型进行约束决策。ProvMind在双分布外分割上达到52.84%准确率，显著优于提示、检索增强及监督微调基线。
原文摘要 · Abstract (English)
Materials process optimization requires reasoning over routes, conditions, tools and causal dependencies, yet most computational formulations flatten synthesis procedures into text or ordered steps. We introduce MatProcBench, a provenance-grounded benchmark constructed from literature-mined MatPROV graphs, to evaluate seven process-reasoning tasks spanning route continuity, step-level variable inference and global causal consistency under both same-split and shift-aware evaluation, including a strict dual-OOD split that combines temporal and material-class shift. We further introduce ProvMind, a process-memory reasoning framework that retrieves analogous training processes, converts them into provenance-aware option-level compatibility scores, and uses a language model for constrained final decision making. ProvMind achieves 52.84\% accuracy on the dual-OOD split, outperforming prompting, retrieval-augmented and supervised fine-tuning baselines.
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。