Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
ViLegalExpert: A Large-Scale Benchmark for Vietnamese Legal Retrieval and Question Answering from Real-World Consultations
Dat Tien Nguyen, Nghia Hieu Nguyen, Anh Thi-Hoang Nguyen +3
Trustworthy Legal AI requires systems that can answer legal questions while grounding their responses in authoritative sources. However, existing Vietnamese legal benchmarks provid…
cs.CL2026
Beyond Atomic Tokens: Factorizing Syllables for Language Model Pretraining
Nghia Hieu Nguyen, Thai Bao Huynh, Binh-An Dinh-Le +4
Conventional tokenizers represent text as characters or statistically derived subwords, overlooking the internal phonological structure of syllables and often requiring large vocab…