Papers by Duen Horng Chau
Dodrio: Exploring Transformer Models with Interactive Visualization (2021.acl-demo)
Copied to clipboard
| Challenge: | Recent research suggests the key may lie in multi-headed attention mechanism’s ability to learn and represent linguistic information. |
| Approach: | They present an open-source visualization tool to analyze attention mechanisms in transformer-based models with linguistic knowledge. |
| Outcome: | Dodrio analyzes attention mechanisms in transformer-based models with linguistic knowledge. |
DiffusionDB: A Large-scale Prompt Gallery Dataset for Text-to-Image Generative Models (2023.acl-long)
Copied to clipboard
| Challenge: | Recent advances in diffusion models have enabled high-quality image generation . generating images with desired details requires proper prompts . |
| Approach: | They analyze syntactic and semantic characteristics of diffusion models and their prompts . they pinpoint specific hyperparameter values and prompt styles that can lead to model errors . |
| Outcome: | The first large-scale text-to-image prompt dataset totals 6.5TB . it contains 14 million images generated by Stable Diffusion, 1.8 million unique prompts, and hyperparameters specified by real users. |
Wordflow: Social Prompt Engineering for Large Language Models (2024.acl-demos)
Copied to clipboard
| Challenge: | Large language models (LLMs) require well-crafted prompts for effective use. |
| Approach: | They propose a social prompt engineering paradigm that leverages social computing techniques to facilitate collaborative prompt design. |
| Outcome: | The proposed paradigm leverages social computing techniques to facilitate prompt design. |
Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing surveys focus on interpretation or safety, but safety and understanding are core motivations for interpretation research. |
| Approach: | They propose a framework that connects interpretation methods, enhancements they inform, and tools that operationalize them. |
| Outcome: | The proposed framework summarizes nearly 70 studies at their intersections and concludes with open challenges and future directions. |
WizMap: Scalable Interactive Visualization for Exploring Large Machine Learning Embeddings (2023.acl-demo)
Copied to clipboard
| Challenge: | Modern machine learning models learn latent embedding representations that capture the domain semantics of training data. |
| Approach: | They propose an interactive visualization tool to help users explore large embeddings by using a multi-resolution summarization method and a familiar map-like interface. |
| Outcome: | The proposed visualization tool scales to millions of embedding points directly in users’ web browsers and computational notebooks without the need for dedicated backend servers. |