# Regularization, Semi-supervision, and Supervision for a Plausible Attention-Based Explanation

arXiv: https://arxiv.org/abs/2501.12775 · HTML: https://mlsanity.com/paper/2501.12775/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 33 references that are in the map.
- First posted on arXiv 22 Jan 2025.

## Builds on (most cited first, 21 of 21)

- [Effective Approaches to Attention-based Neural Machine Translation](https://mlsanity.com/paper/1508.04025/) (2015)
- [Attention is not Explanation](https://mlsanity.com/paper/1902.10186/) (2019)
- [How Contextual are Contextualized Word Representations? Comparing the Geometry of BERT, ELMo, and GPT-2 Embeddings](https://mlsanity.com/paper/1909.00512/) (2019)
- [Annotation Artifacts in Natural Language Inference Data](https://mlsanity.com/paper/1803.02324/) (2018)
- [Attention is not not Explanation](https://mlsanity.com/paper/1908.04626/) (2019)
- [Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?](https://mlsanity.com/paper/2004.03685/) (2020)
- [ERASER: A Benchmark to Evaluate Rationalized NLP Models](https://mlsanity.com/paper/1911.03429/) (2019)
- [e-SNLI: Natural Language Inference with Natural Language Explanations](https://mlsanity.com/paper/1812.01193/) (2018)
- [HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection](https://mlsanity.com/paper/2012.10289/) (2020)
- [Is Attention Interpretable?](https://mlsanity.com/paper/1906.03731/) (2019)
- [From Softmax to Sparsemax: A Sparse Model of Attention and Multi-Label Classification](https://mlsanity.com/paper/1602.02068/) (2016)
- [Teach Me to Explain: A Review of Datasets for Explainable Natural Language Processing](https://mlsanity.com/paper/2102.12060/) (2021)
- [The elephant in the interpretability room: Why use attention as explanation when we have saliency methods?](https://mlsanity.com/paper/2010.05607/) (2020)
- [Learning to Deceive with Attention-Based Explanations](https://mlsanity.com/paper/1909.07913/) (2019)
- [Attention Interpretability Across NLP Tasks](https://mlsanity.com/paper/1909.11218/) (2019)
- [An Information Bottleneck Approach for Controlling Conciseness in Rationale Extraction](https://mlsanity.com/paper/2005.00652/) (2020)
- [Inferring Which Medical Treatments Work from Reports of Clinical Trials](https://mlsanity.com/paper/1904.01606/) (2019)
- [Towards Transparent and Explainable Attention Models](https://mlsanity.com/paper/2004.14243/) (2020)
- [Why Attentions May Not Be Interpretable?](https://mlsanity.com/paper/2006.05656/) (2020)
- [Can Rationalization Improve Robustness?](https://mlsanity.com/paper/2204.11790/) (2022)
- [Who is Killed by Police: Introducing Supervised Attention for Hierarchical LSTMs](https://mlsanity.com/paper/1807.03409/) (2018)

## Built on by (most cited first, 1 of 1)

- [GUI-AIMA: Aligning Intrinsic Multimodal Attention with a Context Anchor for GUI Grounding](https://mlsanity.com/paper/2511.00810/) (2025)

## Abstract (arXiv)

Attention mechanism is contributing to the majority of recent advances in machine learning for natural language processing. Additionally, it results in an attention map that shows the proportional influence of each input in its decision. Empirical studies postulate that attention maps can be provided as an explanation for model output. However, it is still questionable to ask whether this explanation helps regular people to understand and accept the model output (the plausibility of the explanation). Recent studies show that attention weights in the RNN encoders are hardly plausible because they spread on input tokens. We thus propose 3 additional constraints to the learning objective function to improve the plausibility of the attention map: regularization to increase the attention weight sparsity, semi-supervision to supervise the map by a heuristic and supervision by human annotation. Results show that all techniques can improve the attention map plausibility at some level. We also observe that specific instructions for human annotation might have a negative effect on classification performance. Beyond the attention map, the result of experiments on text classification tasks also shows that no matter how the constraint brings the gain, the contextualization layer plays a crucial role in finding the right space for finding plausible tokens.