4 papers · 1 filter
The Rotary Position Embedding May Cause Dimension Inefficiency in Attention Heads for Long-Distance Retrieval
Ting-Rui Chiang, Dani Yogatama
The Rotary Position Embedding (RoPE) is widely used in the attention heads of many large language models (LLM). It rotates dimensions in the query and the key vectors by different…
Pelican Soup Framework: A Theoretical Framework for Language Model Capabilities
Ting-Rui Chiang, Dani Yogatama
In this work, we propose a simple theoretical framework, Pelican Soup, aiming to better understand how pretraining allows LLMs to (1) generalize to unseen instructions and (2) perf…
On Retrieval Augmentation and the Limitations of Language Model Training
Ting-Rui Chiang, Xinyan Velocity Yu, Joshua Robinson +3
Augmenting a language model (LM) with -nearest neighbors (NN) retrieval on its training data alone can decrease its perplexity, though the underlying reasons for this remain…
The Distributional Hypothesis Does Not Fully Explain the Benefits of Masked Language Model Pretraining
Ting-Rui Chiang, Dani Yogatama
We analyze the masked language modeling pretraining objective function from the perspective of the distributional hypothesis. We investigate whether better sample efficiency and th…