Automated Molecular Concept Generation and Labeling with Large Language Models
Not on the map. Why?
Abstract (arXiv)
Artificial intelligence (AI) is transforming scientific research, with explainable AI methods like concept-based models (CMs) showing promise for new discoveries. However, in molecular science, CMs are less common than black-box models like Graph Neural Networks (GNNs), due to their need for predefined concepts and manual labeling. This paper introduces the Automated Molecular Concept (AutoMolCo) framework, which leverages Large Language Models (LLMs) to automatically generate and label predictive molecular concepts. Through iterative concept refinement, AutoMolCo enables simple linear models to outperform GNNs and LLM in-context learning on several benchmarks. The framework operates without human knowledge input, overcoming limitations of existing CMs while maintaining explainability and allowing easy intervention. Experiments on MoleculeNet and High-Throughput Experimentation (HTE) datasets demonstrate that AutoMolCo-induced explainable CMs are beneficial for molecular science research.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 26 of its 51 references that are in the map. First posted on arXiv 13 Jun 2024.
Builds on
26 of 51 references.
References · 26
- 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
- 2019Language Models as Knowledge Bases?cited by 1,922
- 2017MoleculeNet: A Benchmark for Molecular Machine Learningcited by 1,037
- 2020Concept Bottleneck Modelscited by 1,022
- 2020Explainability in Graph Neural Networks: A Taxonomic Surveycited by 383
- 2018Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understandingcited by 304
- 2023Label-Free Concept Bottleneck Modelscited by 282
- 2021On Explainability of Graph Neural Networks via Subgraph Explorationscited by 280
- 2019On Completeness-aware Concept-Based Explanations in Deep Neural Networkscited by 239
- 2020Concept Whitening for Interpretable Image Recognitioncited by 225
- 2023GPT4Graph: Can Large Language Models Understand Graph Structured Data ? An Empirical Evaluation and Benchmarkingcited by 209
- 2023Large Language Models on Graphs: A Comprehensive Surveycited by 190
14 more
- 2023What can Large Language Models do in chemistry? A comprehensive benchmark on eight taskscited by 179
- 2022A Review on Language Models as Knowledge Basescited by 156
- 2024LlaSMol: Advancing Large Language Models for Chemistry with a Large-Scale, Comprehensive, High-Quality Instruction Tuning Datasetcited by 124
- 2023Artificial Intelligence for Science in Quantum, Atomistic, and Continuum Systemscited by 118
- 2023Graph-ToolFormer: To Empower LLMs with Graph Reasoning Ability via Prompt Augmented by ChatGPTcited by 78
- 2019Interpretability Beyond Classification Output: Semantic Bottleneck Networkscited by 49
- 2022GStarX: Explaining Graph Neural Networks with Structure-Aware Cooperative Gamescited by 42
- 2021GCExplainer: Human-in-the-Loop Concept-based Explanations for Graph Neural Networkscited by 35
- 2022Global Concept-Based Interpretability for Graph Neural Networks via Neuron Analysiscited by 32
- 2022Causal Proxy Models for Concept-Based Model Explanationscited by 29
- 2022Molecular Representation Learning via Heterogeneous Motif Graph Neural Networkscited by 23
- 2022Encoding Concepts in Graph Neural Networkscited by 18
- 2018Semantic bottleneck for computer vision taskscited by 10
- 2022Do graph neural networks learn traditional jet substructure?cited by 4
Built on by
Citing papers per year: 2025: 1; 2026: 1.
2 papers.