Showing 2026Show all
2 papers · 1 filter
cs.CL2026
Domain-Agnostic Neural Topic Modeling with Contextual Token-Level Semantic Graph Representation
Seung-Won Seo, Won Ik Cho, Yongmin Yoo
Recent advances in neural topic models with pre-trained language models (PLMs) have achieved strong performance by leveraging general-domain pre-training, yet their topic interpret…
cs.CL2026
From National Curricula to Cultural Awareness: Constructing Open-Ended Culture-Specific Question Answering Dataset
Haneul Yoo, Won Ik Cho, Geunhye Kim +1
Large language models (LLMs) achieve strong performance on many tasks, but their progress remains uneven across languages and cultures, often reflecting values latent in English-ce…