System Report for CCL25-Eval Task 5: New Dataset and LoRA-Fine-Tuned Qwen2.5
Researchers have developed a new dataset, CCPoetry-49K, containing over 49,000 instruction-response pairs specifically for classical Chinese poetry analysis. They then fine-tuned the Qwen2.5-14B model using Low-Rank Adaptation (LoRA) to create PoetryQwen, a domain-specialized LLM. This new model achieved a score of 0.757 on the CCL25-Eval Task 5 benchmark, outperforming the baseline Qwen2.5-14B-Instruct by 9.7% and demonstrating significant improvements in precise translation and emotional understanding of classical poetry. AI
IMPACT Enhances LLM capabilities for nuanced tasks like classical poetry translation and emotional inference, potentially paving the way for more specialized AI applications.