SpectraQuery: A Hybrid Retrieval-Augmented Conversational Assistant for Battery Science

TL;DR

SpectraQuery is a hybrid conversational assistant that integrates structured experimental data with scientific literature, enabling accurate, grounded, and explainable reasoning in battery science through combined semantic parsing and retrieval methods.

Contribution

It introduces a novel hybrid retrieval-augmented framework that unifies structured data and literature for scientific reasoning, with high accuracy and expert-rated performance.

Findings

80% of SQL queries are fully correct

Answer groundedness reaches 93-97% with retrieved passages

High expert ratings on accuracy and relevance (4.1-4.6/5)

Abstract

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.