activity
20232025
most citedTracing the Roots of Facts in Multilingual Language Models: Independent, Shared, and Transferred Knowledge

1 citations · 1 across the 2 of their papers we have counts for

collaborators

5 papers

cs.CL2025

Tracing Multilingual Knowledge Acquisition Dynamics in Domain Adaptation: A Case Study of English-Japanese Biomedical Adaptation

Xin Zhao, Naoki Yoshinaga, Yuma Tsuta +1

Multilingual domain adaptation (ML-DA) is widely used to learn new domain knowledge across languages into large language models (LLMs). Although many methods have been proposed to…

cs.CL2024

Neuron Empirical Gradient: Discovering and Quantifying Neurons Global Linear Controllability

Xin Zhao, Zehui Jiang, Naoki Yoshinaga

While feed-forward neurons in pre-trained language models (PLMs) can encode knowledge, past research targeted a small subset of neurons that heavily influence outputs. This leaves…

cs.CL2024

What Matters in Memorizing and Recalling Facts? Multifaceted Benchmarks for Knowledge Probing in Language Models

Xin Zhao, Naoki Yoshinaga, Daisuke Oba

Language models often struggle with handling factual knowledge, exhibiting factual hallucination issue. This makes it vital to evaluate the models' ability to recall its parametric…

cs.CL20241 cited

Tracing the Roots of Facts in Multilingual Language Models: Independent, Shared, and Transferred Knowledge

Xin Zhao, Naoki Yoshinaga, Daisuke Oba

Acquiring factual knowledge for language models (LMs) in low-resource languages poses a serious challenge, thus resorting to cross-lingual transfer in multilingual LMs (ML-LMs). In…

cs.CL2023

Summarization-based Data Augmentation for Document Classification

Yueguan Wang, Naoki Yoshinaga

Despite the prevalence of pretrained language models in natural language understanding tasks, understanding lengthy text such as document is still challenging due to the data spars…