{"ID":2883371,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.09115","arxiv_id":"2508.09115","title":"SinLlama -- A Large Language Model for Sinhala","abstract":"Low-resource languages such as Sinhala are often overlooked by open-source Large Language Models (LLMs). In this research, we extend an existing multilingual LLM (Llama-3-8B) to better serve Sinhala. We enhance the LLM tokenizer with Sinhala specific vocabulary and perform continual pre-training on a cleaned 10 million Sinhala corpus, resulting in the SinLlama model. This is the very first decoder-based open-source LLM with explicit Sinhala support. When SinLlama was instruction fine-tuned for three text classification tasks, it outperformed base and instruct variants of Llama-3-8B by a significant margin.","short_abstract":"Low-resource languages such as Sinhala are often overlooked by open-source Large Language Models (LLMs). In this research, we extend an existing multilingual LLM (Llama-3-8B) to better serve Sinhala. We enhance the LLM tokenizer with Sinhala specific vocabulary and perform continual pre-training on a cleaned 10 million...","url_abs":"https://arxiv.org/abs/2508.09115","url_pdf":"https://arxiv.org/pdf/2508.09115v4","authors":"[\"H. W. K. Aravinda\",\"Rashad Sirajudeen\",\"Samith Karunathilake\",\"Nisansa de Silva\",\"Surangika Ranathunga\",\"Rishemjit Kaur\"]","published":"2025-08-12T17:49:34Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}