Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2601.13105 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914263753293824 |
|---|---|
| author | Kaipeng, Liu Ling, Wu |
| author_facet | Kaipeng, Liu Ling, Wu |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_13105 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Leveraging Lora Fine-Tuning and Knowledge Bases for Construction Identification Kaipeng, Liu Ling, Wu Computation and Language J.5 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. |
| title | Leveraging Lora Fine-Tuning and Knowledge Bases for Construction Identification |
| topic | Computation and Language J.5 |
| url | https://arxiv.org/abs/2601.13105 |