KnowLA: Enhancing Parameter-efficient Finetuning with Knowledgeable Adaptation

Xindi Luo, Zequn Sun, Jing Zhao, Zhe Zhao, Wei Hu


Abstract
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 KnowLA can help activate the relevant parameterized knowledge in an LLM to answer a question without changing its parameters or input prompts.
Anthology ID:
2024.naacl-long.396
Volume:
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Kevin Duh, Helena Gomez, Steven Bethard
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
7146–7159
Language:
URL:
https://aclanthology.org/2024.naacl-long.396
DOI:
Bibkey:
Cite (ACL):
Xindi Luo, Zequn Sun, Jing Zhao, Zhe Zhao, and Wei Hu. 2024. KnowLA: Enhancing Parameter-efficient Finetuning with Knowledgeable Adaptation. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 7146–7159, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
KnowLA: Enhancing Parameter-efficient Finetuning with Knowledgeable Adaptation (Luo et al., NAACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.naacl-long.396.pdf
Copyright:
 2024.naacl-long.396.copyright.pdf