A Multiscale Visualization Of Attention In The Transformer Model · Awesome LLM Papers Contribute to LLM-Bible

Awesome LLM Papers

A curated collection of research papers on Large Language Models (LLMs), transformers, prompting, fine-tuning, and multi-modal systems. Maintained by Sean Moran.

Contact Sean Moran about this survey or website. Made with Jekyll and Hyde.

A Multiscale Visualization Of Attention In The Transformer Model

Jesse Vig. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: System Demonstrations 2019 – 262 citations

[Paper]    
Model Architecture Attention Mechanism Ethics and Bias GPT Transformer Applications BERT

The Transformer is a sequence model that forgoes traditional recurrent architectures in favor of a fully attention-based approach. Besides improving performance, an advantage of using attention is that it can also help to interpret a model by showing how the model assigns weight to different input elements. However, the multi-layer, multi-head attention mechanism in the Transformer model can be difficult to decipher. To make the model more accessible, we introduce an open-source tool that visualizes attention at multiple scales, each of which provides a unique perspective on the attention mechanism. We demonstrate the tool on BERT and OpenAI GPT-2 and present three example use cases: detecting model bias, locating relevant attention heads, and linking neurons to model behavior.

Similar Work