Picture for James Wexler

James Wexler

ConstitutionalExperts: Training a Mixture of Principle-based Prompts

Add code
Mar 07, 2024
Figure 1 for ConstitutionalExperts: Training a Mixture of Principle-based Prompts
Figure 2 for ConstitutionalExperts: Training a Mixture of Principle-based Prompts
Figure 3 for ConstitutionalExperts: Training a Mixture of Principle-based Prompts
Figure 4 for ConstitutionalExperts: Training a Mixture of Principle-based Prompts
Viaarxiv icon

Automatic Histograms: Leveraging Language Models for Text Dataset Exploration

Add code
Feb 21, 2024
Figure 1 for Automatic Histograms: Leveraging Language Models for Text Dataset Exploration
Figure 2 for Automatic Histograms: Leveraging Language Models for Text Dataset Exploration
Figure 3 for Automatic Histograms: Leveraging Language Models for Text Dataset Exploration
Figure 4 for Automatic Histograms: Leveraging Language Models for Text Dataset Exploration
Viaarxiv icon

LLM Comparator: Visual Analytics for Side-by-Side Evaluation of Large Language Models

Add code
Feb 16, 2024
Viaarxiv icon

ConstitutionMaker: Interactively Critiquing Large Language Models by Converting Feedback into Principles

Add code
Oct 24, 2023
Figure 1 for ConstitutionMaker: Interactively Critiquing Large Language Models by Converting Feedback into Principles
Figure 2 for ConstitutionMaker: Interactively Critiquing Large Language Models by Converting Feedback into Principles
Figure 3 for ConstitutionMaker: Interactively Critiquing Large Language Models by Converting Feedback into Principles
Figure 4 for ConstitutionMaker: Interactively Critiquing Large Language Models by Converting Feedback into Principles
Viaarxiv icon

Analyzing a Caching Model

Add code
Dec 13, 2021
Figure 1 for Analyzing a Caching Model
Figure 2 for Analyzing a Caching Model
Figure 3 for Analyzing a Caching Model
Figure 4 for Analyzing a Caching Model
Viaarxiv icon

Best of both worlds: local and global explanations with human-understandable concepts

Add code
Jun 16, 2021
Figure 1 for Best of both worlds: local and global explanations with human-understandable concepts
Figure 2 for Best of both worlds: local and global explanations with human-understandable concepts
Figure 3 for Best of both worlds: local and global explanations with human-understandable concepts
Figure 4 for Best of both worlds: local and global explanations with human-understandable concepts
Viaarxiv icon

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

Add code
Aug 12, 2020
Figure 1 for The Language Interpretability Tool: Extensible, Interactive Visualizations and Analysis for NLP Models
Figure 2 for The Language Interpretability Tool: Extensible, Interactive Visualizations and Analysis for NLP Models
Figure 3 for The Language Interpretability Tool: Extensible, Interactive Visualizations and Analysis for NLP Models
Figure 4 for The Language Interpretability Tool: Extensible, Interactive Visualizations and Analysis for NLP Models
Viaarxiv icon

The Bach Doodle: Approachable music composition with machine learning at scale

Add code
Jul 14, 2019
Figure 1 for The Bach Doodle: Approachable music composition with machine learning at scale
Figure 2 for The Bach Doodle: Approachable music composition with machine learning at scale
Figure 3 for The Bach Doodle: Approachable music composition with machine learning at scale
Figure 4 for The Bach Doodle: Approachable music composition with machine learning at scale
Viaarxiv icon

The What-If Tool: Interactive Probing of Machine Learning Models

Add code
Jul 09, 2019
Figure 1 for The What-If Tool: Interactive Probing of Machine Learning Models
Figure 2 for The What-If Tool: Interactive Probing of Machine Learning Models
Figure 3 for The What-If Tool: Interactive Probing of Machine Learning Models
Figure 4 for The What-If Tool: Interactive Probing of Machine Learning Models
Viaarxiv icon

Automating Interpretability: Discovering and Testing Visual Concepts Learned by Neural Networks

Add code
Feb 07, 2019
Figure 1 for Automating Interpretability: Discovering and Testing Visual Concepts Learned by Neural Networks
Figure 2 for Automating Interpretability: Discovering and Testing Visual Concepts Learned by Neural Networks
Figure 3 for Automating Interpretability: Discovering and Testing Visual Concepts Learned by Neural Networks
Figure 4 for Automating Interpretability: Discovering and Testing Visual Concepts Learned by Neural Networks
Viaarxiv icon