arXiv cs.CL· Dikshya Mohanty, Manoj Praveen Nandigama, Kuldeepsinh Raj, Sourav Kanti Maiti, Jiannan Yang, Ruiqi Luo, Srinivasa Phani Madhav Marupudi, Mounika Geriki, Prayag Raghunandan, Puneet Lingutla, Tengfei Ma, Niranjan Balasubramanian, Nav Nidhi Rajput·· 11 小时前AI 评分38
ElectroChemLLM：面向高保真电化学信息学的多模态 LLM 流水线
ElectroChemLLM: A Multimodal LLM Pipeline for High-Fidelity Electrochemical Informatics
AI 导读
ElectroChemLLM 是一个多模态信息抽取流水线，可从非结构化科学 PDF 中联合识别电解质组成、电极材料、电池配置及其理化性质，结合混合文档解析与视觉能力 LLM 编排，跨文本、表格和图表提取可验证的结构化数据。在 232 篇人工标注论文基准的电池电解质子集上，其 F-1 分数达 0.97，并已用于构建覆盖 15,000 篇电化学研究文章的结构化数据库 ElectroChemDB。
正文 · 原文
Authors:Dikshya Mohanty, Manoj Praveen Nandigama, Kuldeepsinh Raj, Sourav Kanti Maiti, Jiannan Yang, Ruiqi Luo, Srinivasa Phani Madhav Marupudi, Mounika Geriki, Prayag Raghunandan, Puneet Lingutla, Tengfei Ma, Niranjan Balasubramanian, Nav Nidhi Rajput
Abstract:Electrochemistry is central to solving many modern-day challenges, including energy storage systems for a sustainable future, and its advancement relies heavily on the data from past findings. Existing automated pipelines are limited by text-only architectures, context fragmentation, and numerical hallucinations - collectively preventing accurate, large-scale curation of property databases. We introduce ElectrochemLLM, a multimodal information extraction pipeline that jointly identifies structured electrochemical records encompassing electrolyte compositions, electrode materials, cell configurations, and their measured physicochemical properties from unstructured scientific PDFs at scale. By combining hybrid document parsing with vision-capable LLM orchestration, the pipeline extracts verifiable, structured data across text, tables, and figures. Evaluated on the battery-electrolyte subset of our manually annotated benchmark of 232 papers, ElectrochemLLM achieves an F-1 score of 0.97, and has been applied to curate ElectroChemDB, a structured database spanning 15,000 electrochemical research articles. We demonstrate the utility of this resource by training machine learning models for electrolyte property prediction, illustrating a complete pathway from unstructured literature to predictive materials discovery.
| Subjects: | Computation and Language (cs.CL); Databases (cs.DB); Information Retrieval (cs.IR); Machine Learning (cs.LG) |
| Cite as: | arXiv:2611.00638 [cs.CL] |
| (or arXiv:2611.00638v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2611.00638 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Dikshya Mohanty [view email]
[v1]
Sat, 31 Oct 2026 05:05:27 UTC (12,593 KB)
来源：arXiv cs.CL · arxiv.org