Leveraging Lora Fine-Tuning and Knowledge Bases for Construction Identification
This work addresses a specific linguistic analysis problem for NLP researchers, representing an incremental advancement in construction identification.
The study tackled automatic identification of the English ditransitive construction by integrating LoRA fine-tuning with a RAG framework, achieving significant performance improvements over baseline models in binary classification on annotated corpus data.
This study investigates the automatic identification of the English ditransitive construction by integrating LoRA-based fine-tuning of a large language model with a Retrieval-Augmented Generation (RAG) framework.A binary classification task was conducted on annotated data from the British National Corpus. Results demonstrate that a LoRA-fine-tuned Qwen3-8B model significantly outperformed both a native Qwen3-MAX model and a theory-only RAG system. Detailed error analysis reveals that fine-tuning shifts the model's judgment from a surface-form pattern matching towards a more semantically grounded understanding based.