# Do Transformer Models Show Similar Attention Patterns to Task-Specific Human Gaze?

arXiv: https://arxiv.org/abs/2205.10226 · HTML: https://mlsanity.com/paper/2205.10226/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 101 references that are in the map.
- First posted on arXiv 25 Apr 2022.

## Builds on (most cited first, 30 of 39)

- [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)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Explanation in Artificial Intelligence: Insights from the Social Sciences](https://mlsanity.com/paper/1706.07269/) (2017)
- [Convolutional Neural Networks for Sentence Classification](https://mlsanity.com/paper/1408.5882/) (2014)
- [What Does BERT Look At? An Analysis of BERT's Attention](https://mlsanity.com/paper/1906.04341/) (2019)
- [Attention is not Explanation](https://mlsanity.com/paper/1902.10186/) (2019)
- [Quantifying Attention Flow in Transformers](https://mlsanity.com/paper/2005.00928/) (2020)
- [Attention is not not Explanation](https://mlsanity.com/paper/1908.04626/) (2019)
- [Transformer Interpretability Beyond Attention Visualization](https://mlsanity.com/paper/2012.09838/) (2020)
- [Is Attention Interpretable?](https://mlsanity.com/paper/1906.03731/) (2019)
- [Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers](https://mlsanity.com/paper/2103.15679/) (2021)
- [A Structured Self-attentive Sentence Embedding](https://mlsanity.com/paper/1703.03130/) (2017)
- [One Billion Word Benchmark for Measuring Progress in Statistical Language Modeling](https://mlsanity.com/paper/1312.3005/) (2013)
- [Revealing the Dark Secrets of BERT](https://mlsanity.com/paper/1908.08593/) (2019)
- [Masked Language Modeling and the Distributional Hypothesis: Order Word Matters Pre-training for Little](https://mlsanity.com/paper/2104.06644/) (2021)
- [Pathologies of Neural Models Make Interpretations Difficult](https://mlsanity.com/paper/1804.07781/) (2018)
- [Human Attention in Visual Question Answering: Do Humans and Deep Networks Look at the Same Regions?](https://mlsanity.com/paper/1606.03556/) (2016)
- [XAI for Transformers: Better Explanations through Conservative Propagation](https://mlsanity.com/paper/2202.07304/) (2022)
- [DeepGaze II: Reading fixations from deep features trained on object recognition](https://mlsanity.com/paper/1610.01563/) (2016)
- ["What is Relevant in a Text Document?": An Interpretable Machine Learning Approach](https://mlsanity.com/paper/1612.07843/) (2016)
- [Quantifying Interpretability and Trust in Machine Learning Systems](https://mlsanity.com/paper/1901.08558/) (2019)
- [Improving Natural Language Processing Tasks with Human Gaze-Guided Neural Attention](https://mlsanity.com/paper/2010.07891/) (2020)
- [Object Referring in Videos with Language and Human Gaze](https://mlsanity.com/paper/1801.01582/) (2018)
- [Explaining Predictions of Non-Linear Classifiers in NLP](https://mlsanity.com/paper/1606.07298/) (2016)
- [Correlating neural and symbolic representations of language](https://mlsanity.com/paper/1905.06401/) (2019)
- [Interpreting Attention Models with Human Visual Attention in Machine Reading Comprehension](https://mlsanity.com/paper/2010.06396/) (2020)
- [Multilingual Language Models Predict Human Reading Behavior](https://mlsanity.com/paper/2104.05433/) (2021)
- [CogniVal: A Framework for Cognitive Word Embedding Evaluation](https://mlsanity.com/paper/1909.09001/) (2019)

## Built on by (most cited first, 20 of 20)

- [Towards Faithful Model Explanation in NLP: A Survey](https://mlsanity.com/paper/2209.11326/) (2022)
- [Towards a Mechanistic Interpretation of Multi-Step Reasoning Capabilities of Language Models](https://mlsanity.com/paper/2310.14491/) (2023)
- [Mechanistic Interpretability of Emotion Inference in Large Language Models](https://mlsanity.com/paper/2502.05489/) (2025)
- [Rather a Nurse than a Physician -- Contrastive Explanations under Investigation](https://mlsanity.com/paper/2310.11906/) (2023)
- [A Close Look at Decomposition-based XAI-Methods for Transformer Language Models](https://mlsanity.com/paper/2502.15886/) (2025)
- [WebQAmGaze: A Multilingual Webcam Eye-Tracking-While-Reading Dataset](https://mlsanity.com/paper/2303.17876/) (2023)
- [Probing Large Language Models from A Human Behavioral Perspective](https://mlsanity.com/paper/2310.05216/) (2023)
- [EMTeC: A Corpus of Eye Movements on Machine-Generated Texts](https://mlsanity.com/paper/2408.04289/) (2024)
- [Explainable Compliance Detection with Multi-Hop Natural Language Inference on Assurance Case Structure](https://mlsanity.com/paper/2506.08713/) (2025)
- [Every word counts: A multilingual analysis of individual human alignment with model attention](https://mlsanity.com/paper/2210.04963/) (2022)
- [Gaze-Guided Learning: Avoiding Shortcut Bias in Visual Classification](https://mlsanity.com/paper/2504.05583/) (2025)
- [OASST-ETC Dataset: Alignment Signals from Eye-tracking Analysis of LLM Responses](https://mlsanity.com/paper/2503.10927/) (2025)
- [Integrating Cognitive Processing Signals into Language Models: A Review of Advances, Applications and Future Directions](https://mlsanity.com/paper/2504.06843/) (2025)
- [Attention Alignment Between Humans and Vision-Language Models](https://mlsanity.com/paper/2606.17410/) (2026)
- [Explanation on Pretraining Bias of Finetuned Vision Transformer](https://mlsanity.com/paper/2211.15428/) (2022)
- [Task Decoding based on Eye Movements using Synthetic Data Augmentation](https://mlsanity.com/paper/2509.11547/) (2025)
- [Evaluating Webcam-based Gaze Data as an Alternative for Human Rationale Annotations](https://mlsanity.com/paper/2402.19133/) (2024)
- [D-FaST: Cognitive Signal Decoding with Disentangled Frequency-Spatial-Temporal Attention](https://mlsanity.com/paper/2406.02602/) (2024)
- [Do We Really Need GNNs with Explicit Structural Modeling? MLPs Suffice for Language Model Representations](https://mlsanity.com/paper/2506.21682/) (2025)
- [Tracing How Annotators Think: Augmenting Preference Judgments with Reading Processes](https://mlsanity.com/paper/2511.21912/) (2025)

## Abstract (arXiv)

Learned self-attention functions in state-of-the-art NLP models often correlate with human attention. We investigate whether self-attention in large-scale pre-trained language models is as predictive of human eye fixation patterns during task-reading as classical cognitive models of human attention. We compare attention functions across two task-specific reading datasets for sentiment analysis and relation extraction. We find the predictiveness of large-scale pre-trained self-attention for human attention depends on `what is in the tail', e.g., the syntactic nature of rare contexts. Further, we observe that task-specific fine-tuning does not increase the correlation with human task-specific reading. Through an input reduction experiment we give complementary insights on the sparsity and fidelity trade-off, showing that lower-entropy attention vectors are more faithful.