Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
When a Name Is Not a Name: A Benchmark Dataset and Distilled Reasoning for Culturally Entangled Bangla Homographs in Low-Resource LLMs
Md. Asaduzzaman Shuvo
Many Bangla words are at once personal names and culturally loaded common nouns, "Maya" is both a girl's name and a word for affectionate compassion. Choosing the right reading dem…
cs.CL2026
Polite on the Surface, Broken in Practice: A Curated Dataset for Fixing Generation and Register Failures in Low-Resource Bangla Text Generation
Md. Asaduzzaman Shuvo, Mahedi Hasan, Md. Tashin Parvez +2
Recent advances in Multilingual Large Language Models (MLLMs) have significantly enhanced cross-lingual conversational capabilities, yet modeling culturally nuanced and context-dep…