Výsledky vyhledávání

Report

Why We Build Local Large Language Models: An Observational Analysis from 35 Japanese and Multilingual LLMs

Autor: Saito, Koshiro, Mizuki, Sakae, Ohi, Masanari, Nakamura, Taishi, Shiotani, Taihei, Maeda, Koki, Ma, Youmi, Hattori, Kakeru, Fujii, Kazuki, Okamoto, Takumi, Ishida, Shigeki, Takamura, Hiroya, Yokota, Rio, Okazaki, Naoaki

Why do we build local large language models (LLMs)? What should a local LLM learn from the target language? Which abilities can be transferred from other languages? Do language-specific scaling laws exist? To explore these research questions, we eval

Externí odkaz: http://arxiv.org/abs/2412.14471

Zobrazit plný text záznamu

Report

Building a Japanese Document-Level Relation Extraction Dataset Assisted by Cross-Lingual Transfer

Autor: Ma, Youmi, Wang, An, Okazaki, Naoaki

Document-level Relation Extraction (DocRE) is the task of extracting all semantic relationships from a document. While studies have been conducted on English DocRE, limited attention has been given to DocRE in non-English languages. This work delves

Externí odkaz: http://arxiv.org/abs/2404.16506

Zobrazit plný text záznamu

Report

Sampling-based Pseudo-Likelihood for Membership Inference Attacks

Autor: Kaneko, Masahiro, Ma, Youmi, Wata, Yuki, Okazaki, Naoaki

Large Language Models (LLMs) are trained on large-scale web data, which makes it difficult to grasp the contribution of each text. This poses the risk of leaking inappropriate data such as benchmarks, personal information, and copyrighted texts in th

Externí odkaz: http://arxiv.org/abs/2404.11262

Zobrazit plný text záznamu

Report

DREEAM: Guiding Attention with Evidence for Improving Document-Level Relation Extraction

Autor: Ma, Youmi, Wang, An, Okazaki, Naoaki

Document-level relation extraction (DocRE) is the task of identifying all relations between each entity pair in a document. Evidence, defined as sentences containing clues for the relationship between an entity pair, has been shown to help DocRE syst

Externí odkaz: http://arxiv.org/abs/2302.08675

Zobrazit plný text záznamu

Report

Named Entity Recognition and Relation Extraction using Enhanced Table Filling by Contextualized Representations

Autor: Ma, Youmi, Hiraoka, Tatsuya, Okazaki, Naoaki

In this study, a novel method for extracting named entities and relations from unstructured text based on the table representation is presented. By using contextualized word embeddings, the proposed method computes representations for entity mentions

Externí odkaz: http://arxiv.org/abs/2010.07522

Zobrazit plný text záznamu