Picture for Jiaoda Li

Jiaoda Li

What Do Language Models Learn in Context? The Structured Task Hypothesis

Add code
Jun 06, 2024
Viaarxiv icon

A Transformer with Stack Attention

Add code
May 07, 2024
Viaarxiv icon

Towards a Mechanistic Interpretation of Multi-Step Reasoning Capabilities of Language Models

Add code
Oct 23, 2023
Viaarxiv icon

Probing via Prompting

Add code
Jul 04, 2022
Figure 1 for Probing via Prompting
Figure 2 for Probing via Prompting
Figure 3 for Probing via Prompting
Figure 4 for Probing via Prompting
Viaarxiv icon

Vision Matters When It Should: Sanity Checking Multimodal Machine Translation Models

Add code
Sep 08, 2021
Figure 1 for Vision Matters When It Should: Sanity Checking Multimodal Machine Translation Models
Figure 2 for Vision Matters When It Should: Sanity Checking Multimodal Machine Translation Models
Viaarxiv icon

Differentiable Subset Pruning of Transformer Heads

Add code
Aug 22, 2021
Figure 1 for Differentiable Subset Pruning of Transformer Heads
Figure 2 for Differentiable Subset Pruning of Transformer Heads
Figure 3 for Differentiable Subset Pruning of Transformer Heads
Figure 4 for Differentiable Subset Pruning of Transformer Heads
Viaarxiv icon