This paper introduces a two-stage approach for adapting Qwen2.5-3B to Tibetan, a low-resource language, using Continual Pretraining (CPT) for linguistic grounding and Supervised Fine-Tuning (SFT) for task specialization. The study demonstrates significant improvements in perplexity and translation quality, along with an in-depth analysis of parameter evolution during adaptation.

This survey comprehensively reviews the latest advancements in generative Information Extraction (IE) using Large Language Models (LLMs), categorizing methods by IE subtasks and techniques while identifying future research directions.