Adapting Large Language Models to Low-Resource Tibetan: A Two-Stage Continual and Supervised Fine-Tuning Study
cs.CL
Submitted: 2025-12-03
Updated: 2026-11-16
Code: https://github.com/clf28/TibetanFinetuning
Terminology
Sources
- GPT-4 Technical Report
- Qwen Technical Report
- No Language Left Behind: Scaling Human-Centered Machine Translation
- Don't Stop Pretraining: Adapt Language Models to Domains and Tasks
- Tibetan Language and AI: A Comprehensive Survey of Resources, Methods and Challenges
- Qwen2.5-Coder Technical Report
- The State and Fate of Linguistic Diversity and Inclusion in the NLP World
- LLaMA: Open and Efficient Foundation Language Models
- TLUE: A Tibetan Language Understanding Evaluation Benchmark
- Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning
- PEFTT: Parameter-Efficient Fine-Tuning for low-resource Tibetan pre-trained language models
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data