4 accepted papers
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 angles according to their positions in the input sequence. For long context modeling, the range of positions may vary a…
Augmenting a language model (LM) with k-nearest neighbors (kNN) retrieval on its training data alone can decrease its perplexity, though the underlying reasons for this remain elusive. In this work, we rule out one previously posited possibility — the “softmax bottleneck.” We then create a new datas…
We analyze the masked language modeling pretraining objective function from the perspective of the Distributional Hypothesis. We investigate whether the better sample efficiency and the better generalization capability of models pretrained with masked language modeling can be attributed to the seman…
While multilingual training is now an essential ingredient in machine translation (MT) systems, recent work has demonstrated that it has different effects in different multilingual settings, such as many-to-one, one-to-many, and many-to-many learning. These training settings expose the encoder and t…