Picture for Aram H. Markosyan

Aram H. Markosyan

Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts

Add code
Feb 26, 2024
Figure 1 for Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts
Figure 2 for Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts
Figure 3 for Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts
Figure 4 for Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts
Viaarxiv icon

Using Captum to Explain Generative Language Models

Dec 09, 2023
Figure 1 for Using Captum to Explain Generative Language Models
Figure 2 for Using Captum to Explain Generative Language Models
Figure 3 for Using Captum to Explain Generative Language Models
Figure 4 for Using Captum to Explain Generative Language Models
Viaarxiv icon

Identifying and Disentangling Spurious Features in Pretrained Image Representations

Jun 22, 2023
Figure 1 for Identifying and Disentangling Spurious Features in Pretrained Image Representations
Figure 2 for Identifying and Disentangling Spurious Features in Pretrained Image Representations
Figure 3 for Identifying and Disentangling Spurious Features in Pretrained Image Representations
Figure 4 for Identifying and Disentangling Spurious Features in Pretrained Image Representations
Viaarxiv icon

Tell Your Story: Task-Oriented Dialogs for Interactive Content Creation

Nov 08, 2022
Figure 1 for Tell Your Story: Task-Oriented Dialogs for Interactive Content Creation
Figure 2 for Tell Your Story: Task-Oriented Dialogs for Interactive Content Creation
Figure 3 for Tell Your Story: Task-Oriented Dialogs for Interactive Content Creation
Figure 4 for Tell Your Story: Task-Oriented Dialogs for Interactive Content Creation
Viaarxiv icon

Memorization Without Overfitting: Analyzing the Training Dynamics of Large Language Models

Add code
May 22, 2022
Figure 1 for Memorization Without Overfitting: Analyzing the Training Dynamics of Large Language Models
Figure 2 for Memorization Without Overfitting: Analyzing the Training Dynamics of Large Language Models
Figure 3 for Memorization Without Overfitting: Analyzing the Training Dynamics of Large Language Models
Figure 4 for Memorization Without Overfitting: Analyzing the Training Dynamics of Large Language Models
Viaarxiv icon