MolGround: A Benchmark for Molecular Grounding

2025-03-31

AI Summary

Existing molecular understanding methods emphasize descriptive analysis but lack referential (grounded) capability to precisely anchor molecular concepts to atomic- or bond-level structural components. Method: This paper formally introduces and systematically defines the “molecular grounding” task—localizing textual molecular references to specific substructures in molecular graphs—and constructs the first large-scale molecular grounding benchmark (79K QA pairs). We propose a multi-agent collaborative reasoning framework integrating natural language referential resolution, graph neural networks, and molecular graph representation learning to achieve cross-modal, structure-level localization. Contribution/Results: Experiments demonstrate that our approach significantly outperforms strong baselines including GPT-4o. Grounded outputs improve accuracy by 12.3% on molecular image captioning and by 9.7% on Anatomical Therapeutic Chemical (ATC) classification, establishing a new foundation for referential molecular cognition.

Technology Category

• Natural Language Processing: Language Grounding & Multi-modal NLP
• Machine Learning: Graph-based Machine Learning
• Multiagent Systems: Other Foundations of Multi Agent Systems

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Agentic search
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies

Abstract

Current molecular understanding approaches predominantly focus on the descriptive aspect of human perception, providing broad, topic-level insights. However, the referential aspect -- linking molecular concepts to specific structural components -- remains largely unexplored. To address this gap, we propose a molecular grounding benchmark designed to evaluate a model's referential abilities. We align molecular grounding with established conventions in NLP, cheminformatics, and molecular science, showcasing the potential of NLP techniques to advance molecular understanding within the AI for Science movement. Furthermore, we constructed the largest molecular understanding benchmark to date, comprising 79k QA pairs, and developed a multi-agent grounding prototype as proof of concept. This system outperforms existing models, including GPT-4o, and its grounding outputs have been integrated to enhance traditional tasks such as molecular captioning and ATC (Anatomical, Therapeutic, Chemical) classification.

Problem

• Addressing the unexplored referential aspect of molecular understanding
• Creating a benchmark to evaluate molecular grounding abilities
• Leveraging NLP techniques to advance AI for molecular science

Innovation

• Molecular grounding benchmark for referential abilities
• Largest molecular QA benchmark with 79k pairs
• Multi-agent system outperforms GPT-4o