SpectraQuery: A Hybrid Retrieval-Augmented Conversational Assistant for Battery Science
On the map: LLM reasoning → Knowledge- and tool-augmented reasoning
also in 1 more
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 9 of its 64 references that are in the map. First posted on arXiv 14 Jan 2026.
Builds on
9 of 64 references.
References · 9
- 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
- 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
- 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
- 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
- 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 940
- 2022BioGPT: Generative Pre-trained Transformer for Biomedical Text Generation and Miningcited by 531
- 2020HybridQA: A Dataset of Multi-Hop Question Answering over Tabular and Textual Datacited by 263
- 2018TypeSQL: Knowledge-based Type-Aware Neural Text-to-SQL Generationcited by 81
- 2025Detecting Corpus-Level Knowledge Inconsistencies in Wikipedia with Large Language Modelscited by 4
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026DeepEra: A Deep Evidence Reranking Agent for Scientific Retrieval-Augmented Generated Question Answering
- 2026Re-ranking and Late Interaction Drive Retrieval Quality: A Controlled Comparison of RAG Strategies for Scientific Question Answering
- 2025HiPerRAG: High-Performance Retrieval Augmented Generation for Scientific Insights
- 2026EGT-KG: Evidence-Grounded Typed KG Retrieval for Practical Scientific QA with Small Language Models
- 2026VecTree-RAG: An Agentic Retrieval-Augmented Generation Framework Combining Vector and Tree Retrieval for Efficiency and Accuracy
- 2026LitTraceQA: A Benchmark for Multi-Stage Grounding and Verification in Scientific Question Answering
- 2026AnalyticsGPT: An LLM Workflow for Scientometric Question Answering
- 2025SQuAI: Scientific Question-Answering with Multi-Agent Retrieval-Augmented Generation