Tag
This paper investigates cross-lingual alignment in small Japanese-English bilingual language models by probing cultural and pragmatic reasoning, introducing the J-PragEval-v0 benchmark and proposing Pragmatic Representation Steering for inference-time interventions.
This paper proposes a multidimensional text analysis approach combining Japanese NLP metrics and statistical methods to evaluate changes in risk disclosure quality, applied to Japan's 2019 corporate disclosure reforms. The analysis of 19,770 firm-year observations reveals complex shifts such as increased volume accompanied by decreased readability.
A foundational study on applying stylometric authorship attribution to threat intelligence, using Japanese Rakuten reviews to compare TF-IDF+LR, BERT embedding, BERT fine-tuning, and metric learning methods. BERT-FT performed best overall, but TF-IDF+LR proved more stable and efficient when scaling to hundreds of authors.
JFinTEB introduces the first comprehensive benchmark for evaluating Japanese financial text embeddings, addressing a gap in domain-specific and language-specific evaluation resources. The benchmark includes retrieval and classification tasks evaluated across Japanese-specific, multilingual, and commercial embedding models, with datasets and evaluation framework publicly released.