arXiv cs.AI· 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·· 2 小时前AI 评分39
RxnExBench：面向科学文献结构化化学反应提取的视觉语言模型评测基准
RxnExBench: Benchmarking Vision-Language Models for Structured Chemical Reaction Extraction from Scientific Literature
AI 导读
研究者推出 RxnExBench，一个从合成化学文献图表中评测视觉语言模型结构化反应提取能力的多模态基准，包含来自高影响力化学期刊的 3,565 条专家标注反应和 2,361 个分子结构，采用含 15 种反应角色和 26 个核心字段的统一 schema。
正文 · 原文
Authors: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
Abstract:Screen Tables and Substrate Scopes are information-dense figures widely used in synthetic chemistry literature, yet automated extraction of structured reaction data from them remains challenging. We introduce RxnExBench, a multimodal benchmark for fine-grained reaction-level evaluation. Built from high-impact chemistry journals, it contains 3,565 expert-annotated reactions and 2,361 molecular structures. The dataset adopts a unified schema with 15 reaction roles and 26 core fields, supporting downstream AI-for-Chemistry tasks such as retrosynthetic planning, yield prediction, and reaction condition recommendation. RxnExBench further provides a reasoning-driven difficulty taxonomy, a modular annotation pipeline, and the Oracle-MolRec protocol, which disentangles molecular recognition from higher-level reasoning. Evaluation of 9 state-of-the-art VLMs shows that performance degrades substantially as schema complexity and reasoning demands increase. Under the Oracle-MolRec setting, results further reveal that accurate molecular recognition alone is insufficient, with multimodal integration and chemistry-aware reasoning remaining the primary bottlenecks. We release all data and code to facilitate future research in chemistry-aware multimodal understanding and AI-for-Chemistry dataset construction. The dataset and code will be released at this https URL.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.32221 [cs.AI] |
| (or arXiv:2610.32221v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.32221 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Jiaxing Sun [view email]
[v1]
Fri, 23 Oct 2026 06:19:56 UTC (6,858 KB)
来源：arXiv cs.AI · arxiv.org