让电池科学问答同时懂数据和文献，答案有据可查。
SpectraQuery: A Hybrid Retrieval-Augmented Conversational Assistant for Battery Science
- 用自然语言查询统一调用数据库和文献库
- 生成答案93%-97%有依据，SQL正确率约80%
- 适合电池研究者快速整合实验数据与文献
科学推理越来越需要将结构化实验数据与解释性非结构化文献联系起来，但大多数大模型助手无法跨模态联合推理。我们提出SpectraQuery，一种融合关系型拉曼光谱数据库与向量索引文献库的混合自然语言查询框架，采用受SUQL启发的设计。通过语义解析与检索增强生成相结合，SpectraQuery将开放问题转化为协调的SQL查询与文献检索操作，生成带引用的答案，整合数值证据与机理解释。在SQL正确性、答案扎根度、检索有效性及专家评估方面表现优异：生成的SQL查询约80%完全正确，合成答案在10-15个召回段落下达到93%-97%的扎根度，电池科学家对响应的准确性、相关性、可信度和清晰度评分均达4.1-4.6/5。结果表明，混合检索架构能有效支持科学工作流，为高通量实验数据桥接数据与论述。
原文摘要 · Abstract (English)
Scientific reasoning increasingly requires linking structured experimental data with the unstructured literature that explains it, yet most large language model (LLM) assistants cannot reason jointly across these modalities. We introduce SpectraQuery, a hybrid natural-language query framework that integrates a relational Raman spectroscopy database with a vector-indexed scientific literature corpus using a Structured and Unstructured Query Language (SUQL)-inspired design. By combining semantic parsing with retrieval-augmented generation, SpectraQuery translates open-ended questions into coordinated SQL and literature retrieval operations, producing cited answers that unify numerical evidence with mechanistic explanation. Across SQL correctness, answer groundedness, retrieval effectiveness, and expert evaluation, SpectraQuery demonstrates strong performance: approximately 80 percent of generated SQL queries are fully correct, synthesized answers reach 93-97 percent groundedness with 10-15 retrieved passages, and battery scientists rate responses highly across accuracy, relevance, grounding, and clarity (4.1-4.6/5). These results show that hybrid retrieval architectures can meaningfully support scientific workflows by bridging data and discourse for high-volume experimental datasets.
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。