Hybrid Retrieval-Augmented Generation for Real-time Composition Assistance
Keywords: hybrid AI systems, retrieval augmentation, natural language generation, efficient AI
Abstract: Retrieval augmentation enhances performance of traditional language models by incorporating additional context. However, the computational demands for retrieval augmented large language models (LLMs) poses a challenge when applying them to real-time tasks, such as composition assistance. To address this limitation, we propose the Hybrid Retrieval-Augmented Generation (HybridRAG) framework, a novel approach that efficiently combines a cloud-based LLM with a client-side smaller language model through retrieval augmented memory. This integration enables the client model to generate effective responses, benefiting from the LLM's capabilities and contextual information. Additionally, through an asynchronous memory update mechanism, the client model can deliver real-time completions promptly to user inputs without the need to wait for responses from the cloud. Our experiments on Wikitext dataset and Pile subsets demonstrate that HybridRAG significantly improves utility over client-only models while maintaining low latency.
Primary Area: neurosymbolic & hybrid AI systems (physics-informed, logic & formal reasoning, etc.)
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: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.
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.
Submission Number: 3496
Loading