# Dodrio: Exploring Transformer Models with Interactive Visualization

arXiv: https://arxiv.org/abs/2103.14625 · HTML: https://mlsanity.com/paper/2103.14625/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 32 references that are in the map.
- First posted on arXiv 26 Mar 2021.

## Builds on (most cited first, 23 of 23)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI](https://mlsanity.com/paper/1910.10045/) (2019)
- [Show, Attend and Tell: Neural Image Caption Generation with Visual Attention](https://mlsanity.com/paper/1502.03044/) (2015)
- [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)
- [Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned](https://mlsanity.com/paper/1905.09418/) (2019)
- [A Primer in BERTology: What we know about how BERT works](https://mlsanity.com/paper/2002.12327/) (2020)
- [Designing and Interpreting Probes with Control Tasks](https://mlsanity.com/paper/1909.03368/) (2019)
- [Attention is not not Explanation](https://mlsanity.com/paper/1908.04626/) (2019)
- [Weight Poisoning Attacks on Pre-trained Models](https://mlsanity.com/paper/2004.06660/) (2020)
- [A Multiscale Visualization of Attention in the Transformer Model](https://mlsanity.com/paper/1906.05714/) (2019)
- [Visualizing and Understanding Neural Models in NLP](https://mlsanity.com/paper/1506.01066/) (2015)
- [A Diagnostic Study of Explainability Techniques for Text Classification](https://mlsanity.com/paper/2009.13295/) (2020)
- [The Language Interpretability Tool: Extensible, Interactive Visualizations and Analysis for NLP Models](https://mlsanity.com/paper/2008.05122/) (2020)
- [Visual Analytics in Deep Learning: An Interrogative Survey for the Next Frontiers](https://mlsanity.com/paper/1801.06889/) (2018)
- [On Identifiability in Transformers](https://mlsanity.com/paper/1908.04211/) (2019)
- [Attention Interpretability Across NLP Tasks](https://mlsanity.com/paper/1909.11218/) (2019)
- [Reasoning about Entailment with Neural Attention](https://mlsanity.com/paper/1509.06664/) (2015)
- [CNN Explainer: Learning Convolutional Neural Networks with Interactive Visualization](https://mlsanity.com/paper/2004.15004/) (2020)
- [Attention Flows: Analyzing and Comparing Attention Mechanisms in Language Models](https://mlsanity.com/paper/2009.07053/) (2020)
- [Putting Humans in the Natural Language Processing Loop: A Survey](https://mlsanity.com/paper/2103.04044/) (2021)

## Built on by (most cited first, 28 of 28)

- [Interactive and Visual Prompt Engineering for Ad-hoc Task Adaptation with Large Language Models](https://mlsanity.com/paper/2208.07852/) (2022)
- [AttentionViz: A Global View of Transformer Attention](https://mlsanity.com/paper/2305.03210/) (2023)
- [Label2Label: A Language Modeling Framework for Multi-Attribute Learning](https://mlsanity.com/paper/2207.08677/) (2022)
- [GAM Changer: Editing Generalized Additive Models with Interactive Visualization](https://mlsanity.com/paper/2112.03245/) (2021)
- [Probing the Visualization Literacy of Vision Language Models: the Good, the Bad, and the Ugly](https://mlsanity.com/paper/2504.05445/) (2025)
- [Transformer Explainer: Learning LLM Transformers with Interactive Visual Explanation and Experimentation](https://mlsanity.com/paper/2408.04619/) (2024)
- [Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety](https://mlsanity.com/paper/2506.05451/) (2025)
- [Understanding Large Language Model Behaviors through Interactive Counterfactual Generation and Analysis](https://mlsanity.com/paper/2405.00708/) (2024)
- [KnowledgeVIS: Interpreting Language Models by Comparing Fill-in-the-Blank Prompts](https://mlsanity.com/paper/2403.04758/) (2024)
- [Paying More Attention to Self-attention: Improving Pre-trained Language Models via Attention Guiding](https://mlsanity.com/paper/2204.02922/) (2022)
- [LLMMaps -- A Visual Metaphor for Stratified Evaluation of Large Language Models](https://mlsanity.com/paper/2304.00457/) (2023)
- [iScore: Visual Analytics for Interpreting How Language Models Automatically Score Summaries](https://mlsanity.com/paper/2403.04760/) (2024)
- [Transformers, Contextualism, and Polysemy](https://mlsanity.com/paper/2404.09577/) (2024)
- [Visual Analytics for Efficient Image Exploration and User-Guided Image Captioning](https://mlsanity.com/paper/2311.01016/) (2023)
- [Unlearning Comparator: A Visual Analytics System for Comparative Evaluation of Machine Unlearning Methods](https://mlsanity.com/paper/2508.12730/) (2025)
- [Designing a Direct Feedback Loop between Humans and Convolutional Neural Networks through Local Explanations](https://mlsanity.com/paper/2307.04036/) (2023)
- [EL-VIT: Probing Vision Transformer with Interactive Visualization](https://mlsanity.com/paper/2401.12666/) (2024)
- [Visual Analytics for Generative Transformer Models](https://mlsanity.com/paper/2311.12418/) (2023)
- [Modelling Language using Large Language Models](https://mlsanity.com/paper/2404.09579/) (2024)
- [RAGExplorer: A Visual Analytics System for the Comparative Diagnosis of RAG Systems](https://mlsanity.com/paper/2601.12991/) (2026)
- [Attention Flows for General Transformers](https://mlsanity.com/paper/2205.15389/) (2022)
- [AMPLIFY:Attention-based Mixup for Performance Improvement and Label Smoothing in Transformer](https://mlsanity.com/paper/2309.12689/) (2023)
- [POEM: Interactive Prompt Optimization for Enhancing Multimodal Reasoning of Large Language Models](https://mlsanity.com/paper/2406.03843/) (2024)
- [NeuroBreak: Unveil Internal Jailbreak Mechanisms in Large Language Models](https://mlsanity.com/paper/2509.03985/) (2025)
- [ConceptViz: A Visual Analytics Approach for Exploring Concepts in Large Language Models](https://mlsanity.com/paper/2509.20376/) (2025)
- [InTraVisTo: Inside Transformer Visualisation Tool](https://mlsanity.com/paper/2507.13858/) (2025)
- [ViT-Explainer: An Interactive Walkthrough of the Vision Transformer Pipeline](https://mlsanity.com/paper/2604.02182/) (2026)
- [Applications of the Transformer Architecture in AI-Assisted English Reading Comprehension](https://mlsanity.com/paper/2604.23615/) (2026)

## Abstract (arXiv)

Why do large pre-trained transformer-based models perform so well across a wide variety of NLP tasks? Recent research suggests the key may lie in multi-headed attention mechanism's ability to learn and represent linguistic information. Understanding how these models represent both syntactic and semantic knowledge is vital to investigate why they succeed and fail, what they have learned, and how they can improve. We present Dodrio, an open-source interactive visualization tool to help NLP researchers and practitioners analyze attention mechanisms in transformer-based models with linguistic knowledge. Dodrio tightly integrates an overview that summarizes the roles of different attention heads, and detailed views that help users compare attention weights with the syntactic structure and semantic information in the input text. To facilitate the visual comparison of attention weights and linguistic knowledge, Dodrio applies different graph visualization techniques to represent attention weights scalable to longer input text. Case studies highlight how Dodrio provides insights into understanding the attention mechanism in transformer-based models. Dodrio is available at https://poloclub.github.io/dodrio/.