ElectrolyteFM is a unified multi‑property prediction model designed to improve electrolyte formulation design by learning property‑specific representations and cross‑property knowledge through an expert pool and a routing mechanism. The model selectively incorporates shared information for each target property, using residual adapters to refine predictions. Experiments on the Electrolyte12 dataset show a 14.8% reduction in normalized mean absolute error across 12 properties, and on an unseen sodium‑electrolyte dataset it achieves a 6.7% lower conductivity mean absolute error compared to the best baseline.
By Jiaxin Yu, Shuo Wang, Peng Wang, Yongcai Wang, Deying Li
The article examines how scientific literature, often used as a data source for AI in materials science, can contain hidden inaccuracies such as text-figure mismatches, ambiguous axis labels, unit inconsistencies, and missing measurement context. By tracing solid electrolyte conductivity values from original papers to curated datasets, the authors uncover recurrent errors that are numerically plausible yet hard to detect, leading to significant label noise in AI models. A cross-database example demonstrates that ambiguous reporting can cause a 100‑fold error in conductivity values, underscoring the need for traceable reporting, rigorous curation, and validation practices in AI-driven discovery.
By Qian Wang, Ying Li, Ryuhei Sato, Hidemi Kato, Shin-ichi Orimo, Hao Li, Eric Jianfeng Cheng
arXiv:2604. 22938v2 Announce Type: replace-cross Abstract: The promise of data-driven materials discovery remains constrained by the scarcity of large, high-quality, and accessible experimental datasets.
By Zhanzhao Li, Kengran Yang, Qiyao He, Kai Gong
The review traces the development of machine‑learning techniques for extracting materials data and knowledge from scientific literature, progressing from rule‑based pipelines to NLP models, transformer encoders, and finally large language models and agentic systems that handle text, tables, and figures. It highlights how these methods enable the creation of queryable materials databases, knowledge graphs, generic question answering, AI co‑scientists, chatbots, and closed‑loop discovery with autonomous labs. The paper critically evaluates datasets, extraction accuracy, computational costs, and offers practical guidelines, while outlining open challenges such as full tetrahedron extraction, benchmark scarcity, and terminology resolution.
By Aravindan Kamatchi Sundaram, B. Pabitramohan Prusty, Rohit Batra
RxnExBench is a multimodal benchmark designed to evaluate vision‑language models on the task of extracting structured chemical reaction data from dense figures in synthetic chemistry literature. The dataset, compiled from high‑impact journals, contains 3,565 expert‑annotated reactions and 2,361 molecular structures, organized under a unified schema of 15 reaction roles and 26 core fields. It also introduces a difficulty taxonomy, a modular annotation pipeline, and the Oracle‑MolRec protocol to separate molecular recognition from higher‑level reasoning, and shows that current state‑of‑the‑art models struggle as schema complexity and reasoning demands increase.
By Jiaxing Sun, Junyuan Gao, Ruikang Zhang, Hao Zheng, Lingli Ge, Xiao An, Jiang Wu, Huazheng Zeng, Jiahe Song, Chen Zhu, Haote Yang, Jingchao Wang, Lu Chen, Yuanyuan Cao, Ruijie Zhang, Shengxin Lu, Weijia Li, Lijun Wu, Conghui He
arXiv:2607. 09806v1 Announce Type: cross Abstract: Artificial intelligence (AI) is transforming scientific discovery, but its effectiveness is fundamentally limited by the availability of structured scientific knowledge.
By Dibakar Datta