Thrust: Adaptively Propels Large Language Models with External Knowledge

Xinran Zhao, Hongming Zhang, Xiaoman Pan, Wenlin Yao, Dong Yu, Jianshu Chen

Keywords: knowledge-intensive natural language processing, pre-trained language models, instance-level adaptive knowledge usage

TL;DR: We design a novel metric, Thrust, that can decide if we use external knowledge for each instance and observe significant improvement on both cost-efficiency and performance for various knowledge-intensive natural language processing tasks.

Abstract: Large-scale pre-trained language models (PTLM) have achieved great success in various natural language processing (NLP) tasks. Much evidence shows that PTLMs already encode rich knowledge themselves, but knowledge stored in PTLMs can be opaque and static, making external knowledge retrieval necessary. However, there are two major challenges when using external knowledge. First, knowledge indexing and retrieving on large-scale knowledge bases are time costly. Second, knowledge retrieved could be noisy and sometimes misleading. Motivated by the observation that external knowledge is not always required by PTLMs, we investigate an effective and efficient way to apply knowledge only when the knowledge is essential. Specifically, we propose instance-level adaptive propulsion of external knowledge (IAPEK), where we score each instance on whether the PTLMs need the support of external knowledge. To achieve this goal, we design a novel metric, Thrust, which leverages the distribution estimation on seen/training instances. Extensive experiments demonstrate that we can achieve significantly higher cost-efficiency through Thrust compared to the naive usage of external knowledge on 88% of the evaluated tasks with 26% average performance improvement. Such findings further shed light on the real-world practice of knowledge-enhanced LMs with a limited budget for knowledge seeking due to computation latency or costs.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Applications (eg, speech processing, computer vision, NLP)