Natural Language Toolkit for Malaysian language, https://malaya.readthedocs.io/
-
Updated
Mar 26, 2026 - Jupyter Notebook
Natural Language Toolkit for Malaysian language, https://malaya.readthedocs.io/
Human-verified Arabic–Malay benchmark for evaluating RAG faithfulness across Quran and Wikipedia domains 1,140 QA pairs, retrieval + LLM-judge evaluation, and independent second-annotator validation.
Public leaderboard site for GlossoBench — SEA-HELM-style results for Malay, Thai, Vietnamese & low-resource languages
LoRA/QLoRA/AdaLoRA/DoRA/VeRA fine-tuning for RAG faithfulness Arabic (XQuAD) & Malay (Belebele) QA with mT5, self-critical sequence training, and independent NLI verification.
To associate your repository with the malay-nlp topic, visit your repo's landing page and select "manage topics."