Benchmarking Multimodal LLMs on Recognition and Understanding over Chemical Tables
By: Yitong Zhou , Mingyue Cheng , Qingyang Mao and more
Potential Business Impact:
Helps computers understand chemistry tables better.
Chemical tables encode complex experimental knowledge through symbolic expressions, structured variables, and embedded molecular graphics. Existing benchmarks largely overlook this multimodal and domain-specific complexity, limiting the ability of multimodal large language models to support scientific understanding in chemistry. In this work, we introduce ChemTable, a large-scale benchmark of real-world chemical tables curated from the experimental sections of literature. ChemTable includes expert-annotated cell polygons, logical layouts, and domain-specific labels, including reagents, catalysts, yields, and graphical components and supports two core tasks: (1) Table Recognition, covering structure parsing and content extraction; and (2) Table Understanding, encompassing both descriptive and reasoning-oriented question answering grounded in table structure and domain semantics. We evaluated a range of representative multimodal models, including both open-source and closed-source models, on ChemTable and reported a series of findings with practical and conceptual insights. Although models show reasonable performance on basic layout parsing, they exhibit substantial limitations on both descriptive and inferential QA tasks compared to human performance, and we observe significant performance gaps between open-source and closed-source models across multiple dimensions. These results underscore the challenges of chemistry-aware table understanding and position ChemTable as a rigorous and realistic benchmark for advancing scientific reasoning.
Similar Papers
Format Matters: The Robustness of Multimodal LLMs in Reviewing Evidence from Tables and Charts
Computation and Language
Helps computers check science facts from charts.
Evaluating Large Language Models on Multimodal Chemistry Olympiad Exams
Computation and Language
Helps AI understand chemistry pictures and words.
Table as a Modality for Large Language Models
Computation and Language
Helps computers understand charts and tables better.