Self-Knowledge Guided Retrieval Augmentation for Large Language Models

Yile Wang, Peng Li, Maosong Sun, Yang Liu


Abstract
Large language models (LLMs) have shown superior performance without task-specific fine-tuning. Despite the success, the knowledge stored in the parameters of LLMs could still be incomplete and difficult to update due to the computational costs. As complementary, retrieval-based methods can offer non-parametric world knowledge and improve the performance on tasks such as question answering. However, we find that the retrieved knowledge does not always help and even has a negative impact on original responses occasionally. To better make use of both internal knowledge and external world knowledge, we investigate eliciting the model’s ability to recognize what they know and do not know (which is also called “self-knowledge”) and propose Self-Knowledge guided Retrieval augmentation (SKR), a simple yet effective method which can let LLMs refer to the questions they have previously encountered and adaptively call for external resources when dealing with new questions. We evaluate SKR on multiple datasets and demonstrate that it outperforms chain-of-thought based and fully retrieval-based methods by using either InstructGPT or ChatGPT.
Anthology ID:
2023.findings-emnlp.691
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2023
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
10303–10315
Language:
URL:
https://aclanthology.org/2023.findings-emnlp.691
DOI:
10.18653/v1/2023.findings-emnlp.691
Bibkey:
Cite (ACL):
Yile Wang, Peng Li, Maosong Sun, and Yang Liu. 2023. Self-Knowledge Guided Retrieval Augmentation for Large Language Models. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 10303–10315, Singapore. Association for Computational Linguistics.
Cite (Informal):
Self-Knowledge Guided Retrieval Augmentation for Large Language Models (Wang et al., Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-emnlp.691.pdf