Extracting human interpretable structure-property relationships in chemistry using XAI and large language models

Geemi P. Wellawatte, Philippe Schwaller
11/7/2023
physics.chem-phcs.LG

Official code: geemi725/XpertAI (27 stars, MIT, last commit 2025-01-20).

Abstract

Explainable Artificial Intelligence (XAI) is an emerging field in AI that aims to address the opaque nature of machine learning models. Furthermore, it has been shown that XAI can be used to extract input-output relationships, making them a useful tool in chemistry to understand structure-property relationships. However, one of the main limitations of XAI methods is that they are developed for technically oriented users. We propose the XpertAI framework that integrates XAI methods with large language models (LLMs) accessing scientific literature to generate accessible natural language explanations of raw chemical data automatically. We conducted 5 case studies to evaluate the performance of XpertAI. Our results show that XpertAI combines the strengths of LLMs and XAI tools in generating specific, scientific, and interpretable explanations.

View on arXivView PDF

Code Implementations(1)

geemi725/XpertAIOfficial
MIT

Extract structure-functions from data using XAI and LLMs

274PythonSep 17, 20231 years agoMIT

Similar Papers

LLMs for XAI: Future Directions for Explaining Explanations

85% match2024

Towards Symbolic XAI -- Explanation Through Human Understandable Logical Relationships Between Features

84% match1 repo42024

Explainability Techniques for Chemical Language Models

84% match1 repo12023

LLMs for Explainable AI: A Comprehensive Survey

84% match2025

XAI meets LLMs: A Survey of the Relation between Explainable AI and Large Language Models

83% match2024

Assessing the Chemical Intelligence of Large Language Models

83% match1 repo362025

Cite this paper

@article{wellawatte2023extracting,
  title  = {Extracting human interpretable structure-property relationships in chemistry using XAI and large language models},
  author = {Geemi P. Wellawatte and Philippe Schwaller},
  year   = {2023},
  eprint = {2311.04047},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2311.04047v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2311.04047.svg)](https://codeofpaper.com/paper/2311.04047)

Discussion