Jiaoda Li

Latest

• Characterizing the Expressivity of Transformer Language Models
• Probability Distributions Computed by Hard-Attention Transformers
• Unique Hard Attention: A Tale of Two Sides
• A Transformer with Stack Attention
• What Do Language Models Learn in Context? The Structured Task Hypothesis.
• Probing via Prompting
• Differentiable Subset Pruning of Transformer Heads