3 accepted papers
The grammatical knowledge of language models (LMs) is often measured using a benchmark of linguistic minimal pairs, where LMs are presented with a pair of acceptable and unacceptable sentences and required to judge which is more acceptable. Conventional approaches compare sentence probabilities dire…
When training large language models (LLMs), it is common practice to track downstream task performance throughout the training process and select the checkpoint with the highest validation score.However, downstream metrics often exhibit substantial fluctuations, making it difficult to identify the c
The k-nearest-neighbor language model (kNN-LM), one of the retrieval-augmented language models, improves the perplexity for given text by directly accessing a large datastore built from any text data during inference.A widely held hypothesis for the success of kNN-LM is that its explicit memory, i.e…