# Reflective-Net: Learning from Explanations

arXiv: https://arxiv.org/abs/2011.13986 · HTML: https://mlsanity.com/paper/2011.13986/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Nov 2020.

## Built on by (most cited first, 13 of 13)

- [Explainable Artificial Intelligence (XAI) 2.0: A Manifesto of Open Challenges and Interdisciplinary Research Directions](https://mlsanity.com/paper/2310.19775/) (2023)
- [Going Beyond XAI: A Systematic Survey for Explanation-Guided Learning](https://mlsanity.com/paper/2212.03954/) (2022)
- [Explainable Generative AI (GenXAI): A Survey, Conceptualization, and Research Agenda](https://mlsanity.com/paper/2404.09554/) (2024)
- [Introspective Learning : A Two-Stage Approach for Inference in Neural Networks](https://mlsanity.com/paper/2209.08425/) (2022)
- [Learning by Self-Explaining](https://mlsanity.com/paper/2309.08395/) (2023)
- [Explaining Classifiers by Constructing Familiar Concepts](https://mlsanity.com/paper/2203.04109/) (2022)
- [What comes after transformers? -- A selective survey connecting ideas in deep learning](https://mlsanity.com/paper/2408.00386/) (2024)
- [Focus on Likely Classes for Test-Time Prediction](https://mlsanity.com/paper/2505.03819/) (2025)
- [Streamlining models with explanations in the learning loop](https://mlsanity.com/paper/2302.07760/) (2023)
- [Effective Guidance for Model Attention with Simple Yes-no Annotations](https://mlsanity.com/paper/2410.22312/) (2024)
- [IMPACTX: improving model performance by appropriately constraining the training with teacher explanations](https://mlsanity.com/paper/2502.12222/) (2025)
- [Using Phonemes in cascaded S2S translation pipeline](https://mlsanity.com/paper/2504.16234/) (2025)
- [Neural Concept Verifier: Scaling Prover-Verifier Games via Concept Encodings](https://mlsanity.com/paper/2507.07532/) (2025)

## Abstract (arXiv)

We examine whether data generated by explanation techniques, which promote a process of self-reflection, can improve classifier performance. Our work is based on the idea that humans have the ability to make quick, intuitive decisions as well as to reflect on their own thinking and learn from explanations. To the best of our knowledge, this is the first time that the potential of mimicking this process by using explanations generated by explainability methods has been explored. We found that combining explanations with traditional labeled data leads to significant improvements in classification accuracy and training efficiency across multiple image classification datasets and convolutional neural network architectures. It is worth noting that during training, we not only used explanations for the correct or predicted class, but also for other classes. This serves multiple purposes, including allowing for reflection on potential outcomes and enriching the data through augmentation.