Augmented Large Language Models with Parametric Knowledge Guiding
This addresses the issue of domain-specific task performance and data privacy for users of black-box LLMs, though it is incremental as it builds on existing open-source models.
The paper tackles the problem of large language models (LLMs) performing poorly on domain-specific tasks due to limited specialized knowledge and privacy concerns, proposing a Parametric Knowledge Guiding (PKG) framework that enhances black-box LLMs' performance with gains of up to +11.9% on tasks requiring factual, tabular, medical, and multimodal knowledge.
Large Language Models (LLMs) have significantly advanced natural language processing (NLP) with their impressive language understanding and generation capabilities. However, their performance may be suboptimal for domain-specific tasks that require specialized knowledge due to limited exposure to the related data. Additionally, the lack of transparency of most state-of-the-art (SOTA) LLMs, which can only be accessed via APIs, impedes further fine-tuning with domain custom data. Moreover, providing private data to the LLMs' owner leads to data privacy problems. To address these challenges, we propose the novel Parametric Knowledge Guiding (PKG) framework, which equips LLMs with a knowledge-guiding module to access relevant knowledge without altering the LLMs' parameters. Our PKG is based on open-source "white-box" language models, allowing offline memory of any knowledge that LLMs require. We demonstrate that our PKG framework can enhance the performance of "black-box" LLMs on a range of domain knowledge-intensive tasks that require factual (+7.9%), tabular (+11.9%), medical (+3.0%), and multimodal (+8.1%) knowledge.