KnowLA: Enhancing Parameter-efficient Finetuning with Knowledgeable Adaptation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914724710449152 |
|---|---|
| author | Luo, Xindi Sun, Zequn Zhao, Jing Zhao, Zhe Hu, Wei |
| author_facet | Luo, Xindi Sun, Zequn Zhao, Jing Zhao, Zhe Hu, Wei |
| contents | Parameter-efficient finetuning (PEFT) is a key technique for adapting large language models (LLMs) to downstream tasks. In this paper, we study leveraging knowledge graph embeddings to improve the effectiveness of PEFT. We propose a knowledgeable adaptation method called KnowLA. It inserts an adaptation layer into an LLM to integrate the embeddings of entities appearing in the input text. The adaptation layer is trained in combination with LoRA on instruction data. Experiments on six benchmarks with two popular LLMs and three knowledge graphs demonstrate the effectiveness and robustness of KnowLA. We show that \modelname can help activate the relevant parameterized knowledge in an LLM to answer a question without changing its parameters or input prompts. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_14950 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | KnowLA: Enhancing Parameter-efficient Finetuning with Knowledgeable Adaptation Luo, Xindi Sun, Zequn Zhao, Jing Zhao, Zhe Hu, Wei Computation and Language Machine Learning Parameter-efficient finetuning (PEFT) is a key technique for adapting large language models (LLMs) to downstream tasks. In this paper, we study leveraging knowledge graph embeddings to improve the effectiveness of PEFT. We propose a knowledgeable adaptation method called KnowLA. It inserts an adaptation layer into an LLM to integrate the embeddings of entities appearing in the input text. The adaptation layer is trained in combination with LoRA on instruction data. Experiments on six benchmarks with two popular LLMs and three knowledge graphs demonstrate the effectiveness and robustness of KnowLA. We show that \modelname can help activate the relevant parameterized knowledge in an LLM to answer a question without changing its parameters or input prompts. |
| title | KnowLA: Enhancing Parameter-efficient Finetuning with Knowledgeable Adaptation |
| topic | Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2403.14950 |