GTR-CoT: Graph Traversal as Visual Chain of Thought for Molecular Structure Recognition
By: Jingchao Wang , Haote Yang , Jiang Wu and more
Potential Business Impact:
Reads chemical pictures into computer code.
Optical Chemical Structure Recognition (OCSR) is crucial for digitizing chemical knowledge by converting molecular images into machine-readable formats. While recent vision-language models (VLMs) have shown potential in this task, their image-captioning approach often struggles with complex molecular structures and inconsistent annotations. To overcome these challenges, we introduce GTR-Mol-VLM, a novel framework featuring two key innovations: (1) the Graph Traversal as Visual Chain of Thought mechanism that emulates human reasoning by incrementally parsing molecular graphs through sequential atom-bond predictions, and (2) the data-centric principle of Faithfully Recognize What You've Seen, which addresses the mismatch between abbreviated structures in images and their expanded annotations. To support model development, we constructed GTR-CoT-1.3M, a large-scale instruction-tuning dataset with meticulously corrected annotations, and introduced MolRec-Bench, the first benchmark designed for a fine-grained evaluation of graph-parsing accuracy in OCSR. Comprehensive experiments demonstrate that GTR-Mol-VLM achieves superior results compared to specialist models, chemistry-domain VLMs, and commercial general-purpose VLMs. Notably, in scenarios involving molecular images with functional group abbreviations, GTR-Mol-VLM outperforms the second-best baseline by approximately 14 percentage points, both in SMILES-based and graph-based metrics. We hope that this work will drive OCSR technology to more effectively meet real-world needs, thereby advancing the fields of cheminformatics and AI for Science. We will release GTR-CoT at https://github.com/opendatalab/GTR-CoT.
Similar Papers
Vis-CoT: A Human-in-the-Loop Framework for Interactive Visualization and Intervention in LLM Chain-of-Thought Reasoning
Computation and Language
Lets people fix AI's thinking steps.
Integrating Chain-of-Thought for Multimodal Alignment: A Study on 3D Vision-Language Learning
Computation and Language
Teaches computers to understand 3D objects by thinking step-by-step.
MM-CoT:A Benchmark for Probing Visual Chain-of-Thought Reasoning in Multimodal Models
CV and Pattern Recognition
Tests if AI truly sees and thinks.