# Transparent AI for Mathematics: Transformer-Based Large Language Models for Mathematical Entity Relationship Extraction with XAI

arXiv: https://arxiv.org/abs/2603.06348 · HTML: https://mlsanity.com/paper/2603.06348/

## Key facts

- Cited by 2 papers in the map (data through 7 Oct 2026).
- Builds on 12 of its 38 references that are in the map.
- First posted on arXiv 6 Mar 2026.

## Builds on (most cited first, 12 of 12)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books](https://mlsanity.com/paper/1506.06724/) (2015)
- [Exploiting BERT for End-to-End Aspect-based Sentiment Analysis](https://mlsanity.com/paper/1910.00883/) (2019)
- [Learning to Reason Deductively: Math Word Problem Solving as Complex Relation Extraction](https://mlsanity.com/paper/2203.10316/) (2022)
- [MWP-BERT: Numeracy-Augmented Pre-training for Math Word Problem Solving](https://mlsanity.com/paper/2107.13435/) (2021)
- [Experimental Evaluation of Deep Learning models for Marathi Text Classification](https://mlsanity.com/paper/2101.04899/) (2021)
- [Mathematical Word Problem Generation from Commonsense Knowledge Graph and Equations](https://mlsanity.com/paper/2010.06196/) (2020)
- [SHAP values for Explaining CNN-based Text Classification Models](https://mlsanity.com/paper/2008.11825/) (2020)
- [Pretraining and Fine-Tuning Strategies for Sentiment Analysis of Latvian Tweets](https://mlsanity.com/paper/2010.12401/) (2020)
- [Cross-Lingual Text Classification of Transliterated Hindi and Malayalam](https://mlsanity.com/paper/2108.13620/) (2021)
- [Towards Explaining STEM Document Classification using Mathematical Entity Linking](https://mlsanity.com/paper/2109.00954/) (2021)
- [Feature importance to explain multimodal prediction models. A clinical use case](https://mlsanity.com/paper/2404.18631/) (2024)

## Built on by (most cited first, 2 of 2)

- [Privacy Preserving Topic-wise Sentiment Analysis of the Iran Israel USA Conflict Using Federated Transformer Models](https://mlsanity.com/paper/2603.13655/) (2026)
- [Automated Multilabel Mpox Research Classification with Explainable Transformer Models](https://mlsanity.com/paper/2607.26700/) (2026)

## Abstract (arXiv)

Mathematical text understanding is a challenging task due to the presence of specialized entities and complex relationships between them. This study formulates mathematical problem interpretation as a Mathematical Entity Relation Extraction (MERE) task, where operands are treated as entities and operators as their relationships. Transformer-based models are applied to automatically extract these relations from mathematical text, with Bidirectional Encoder Representations from Transformers (BERT) achieving the best performance, reaching an accuracy of 99.39%. To enhance transparency and trust in the model's predictions, Explainable Artificial Intelligence (XAI) is incorporated using Shapley Additive Explanations (SHAP). The explainability analysis reveals how specific textual and mathematical features influence relation prediction, providing insights into feature importance and model behavior. By combining transformer-based learning, a task-specific dataset, and explainable modeling, this work offers an effective and interpretable framework for MERE, supporting future applications in automated problem solving, knowledge graph construction, and intelligent educational systems.