1 citations · 1 across the 8 of their papers we have counts for
8 papers
Measuring Task-Agnostic Training Data Influence Across Language Model Pretraining
Yuto Nishida, Hirokazu Kiyomaru, Yusuke Oda +6
Measuring training data influence consistently across language model pretraining is challenging. It is difficult to select downstream tasks or validation sets representative of a m…
Revisiting Non-Verbatim Memorization in Large Language Models: The Role of Entity Surface Forms
Yuto Nishida, Naoki Shikoda, Yosuke Kishinami +4
Understanding what kinds of factual knowledge large language models (LLMs) memorize is essential for evaluating their reliability and limitations. Entity-based QA is a common frame…
Instability in Downstream Task Performance During LLM Pretraining
Yuto Nishida, Masaru Isonuma, Yusuke Oda
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 va…
Long-Tail Crisis in Nearest Neighbor Language Models
Yuto Nishida, Makoto Morishita, Hiroyuki Deguchi +2
The -nearest-neighbor language model (NN-LM), one of the retrieval-augmented language models, improves the perplexity for given text by directly accessing a large datastore b…
How to Make the Most of LLMs' Grammatical Knowledge for Acceptability Judgments
Yusuke Ide, Yuto Nishida, Justin Vasselli +4
The grammatical knowledge of language models (LMs) is often measured using a benchmark of linguistic minimal pairs, where the LMs are presented with a pair of acceptable and unacce…
Generating Diverse Translation with Perturbed kNN-MT
Yuto Nishida, Makoto Morishita, Hidetaka Kamigaito +1
Generating multiple translation candidates would enable users to choose the one that satisfies their needs. Although there has been work on diversified generation, there exists roo…
knn-seq: Efficient, Extensible kNN-MT Framework
Hiroyuki Deguchi, Hayate Hirano, Tomoki Hoshino +3
k-nearest-neighbor machine translation (kNN-MT) boosts the translation quality of a pre-trained neural machine translation (NMT) model by utilizing translation examples during deco…
Code Transpilation for Hardware Accelerators
Yuto Nishida, Sahil Bhatia, Shadaj Laddad +3
DSLs and hardware accelerators have proven to be very effective in optimizing computationally expensive workloads. In this paper, we propose a solution to the challenge of manually…