Andy Coenen

The Language Interpretability Tool: Extensible, Interactive Visualizations and Analysis for NLP Models

2020 · arXiv (Cornell University)

We present the Language Interpretability Tool (LIT), an open-source platform for visualization and understanding of NLP models. We focus on core questions about model behavior: Why did my model make this prediction? When does it …

A Recipe For Arbitrary Text Style Transfer with Large Language Models

2021 · arXiv (Cornell University)

In this paper, we leverage large language models (LMs) to perform zero-shot text style transfer. We present a prompting method that we call augmented zero-shot learning, which frames style transfer as a sentence rewriting task …

Just Say No to Single Embeddings: Why Your AI Needs Multiple Perspectives

2019 · arXiv (Cornell University)

Note: This is a work in progress document We present empirical evidence that conversations exhibit consistent geometric signatures when projected into different embedding spaces, alongside surprising variability in local feature detection. Analyzing 229 multi-agent AI …