# Explainability Techniques for Chemical Language Models

arXiv: https://arxiv.org/abs/2305.16192 · HTML: https://mlsanity.com/paper/2305.16192/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 57 references that are in the map.
- First posted on arXiv 25 May 2023.

## Builds on (most cited first, 27 of 27)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges](https://mlsanity.com/paper/2104.13478/) (2021)
- [Quantifying Attention Flow in Transformers](https://mlsanity.com/paper/2005.00928/) (2020)
- [Convolutional Networks on Graphs for Learning Molecular Fingerprints](https://mlsanity.com/paper/1509.09292/) (2015)
- [Transformer Interpretability Beyond Attention Visualization](https://mlsanity.com/paper/2012.09838/) (2020)
- [Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers](https://mlsanity.com/paper/2103.15679/) (2021)
- [Not Just a Black Box: Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1605.01713/) (2016)
- [Explaining NonLinear Classification Decisions with Deep Taylor Decomposition](https://mlsanity.com/paper/1512.02479/) (2015)
- [Explainability Techniques for Graph Convolutional Networks](https://mlsanity.com/paper/1905.13686/) (2019)
- [On Calibration and Out-of-domain Generalization](https://mlsanity.com/paper/2102.10395/) (2021)
- [Molecular representation learning with language models and domain-relevant auxiliary tasks](https://mlsanity.com/paper/2011.13230/) (2020)
- [Molecule Attention Transformer](https://mlsanity.com/paper/2002.08264/) (2020)
- [Formal Algorithms for Transformers](https://mlsanity.com/paper/2207.09238/) (2022)
- [Mapping the Space of Chemical Reactions Using Attention-Based Neural Networks](https://mlsanity.com/paper/2012.06051/) (2020)
- [Keeping it Simple: Language Models can learn Complex Molecular Distributions](https://mlsanity.com/paper/2112.03041/) (2021)
- [MolGenSurvey: A Systematic Survey in Machine Learning Models for Molecule Design](https://mlsanity.com/paper/2203.14500/) (2022)
- [Deep Molecular Dreaming: Inverse machine learning for de-novo molecular design and interpretability with surjective representations](https://mlsanity.com/paper/2012.09712/) (2020)
- [Safe Reinforcement Learning From Pixels Using a Stochastic Latent Representation](https://mlsanity.com/paper/2210.01801/) (2022)
- [Recent advances in the Self-Referencing Embedding Strings (SELFIES) library](https://mlsanity.com/paper/2302.03620/) (2023)
- [Neural Payoff Machines: Predicting Fair and Stable Payoff Allocations Among Team Members](https://mlsanity.com/paper/2208.08798/) (2022)

## Built on by (most cited first, 6 of 6)

- [FragNet: A Graph Neural Network for Molecular Property Prediction with Four Levels of Interpretability](https://mlsanity.com/paper/2410.12156/) (2024)
- [Using Cooperative Game Theory to Prune Neural Networks](https://mlsanity.com/paper/2311.10468/) (2023)
- [Conditional Chemical Language Models are Versatile Tools in Drug Discovery](https://mlsanity.com/paper/2507.10273/) (2025)
- [Explainable Multi-View Deep Networks Methodology for Experimental Physics](https://mlsanity.com/paper/2308.08206/) (2023)
- [The Role of Model Architecture and Scale in Predicting Molecular Properties: Insights from Fine-Tuning RoBERTa, BART, and LLaMA](https://mlsanity.com/paper/2405.00949/) (2024)
- [Modelling Chemical Reaction Networks using Neural Ordinary Differential Equations](https://mlsanity.com/paper/2502.19397/) (2025)

## Abstract (arXiv)

Explainability techniques are crucial in gaining insights into the reasons behind the predictions of deep learning models, which have not yet been applied to chemical language models. We propose an explainable AI technique that attributes the importance of individual atoms towards the predictions made by these models. Our method backpropagates the relevance information towards the chemical input string and visualizes the importance of individual atoms. We focus on self-attention Transformers operating on molecular string representations and leverage a pretrained encoder for finetuning. We showcase the method by predicting and visualizing solubility in water and organic solvents. We achieve competitive model performance while obtaining interpretable predictions, which we use to inspect the pretrained model.