@misc{wang2024kblam, author = {Wang, Xi and Mikaelyan, Liana and Isazawa, Taketomo and Hensman, James}, title = {KBLaM: Knowledge Base augmented Language Model}, howpublished = {ArXiv}, year = {2024}, month = {October}, abstract = {In this paper, we propose Knowledge Base augmented Language Model (KBLaM), a new method for augmenting Large Language Models (LLMs) with external knowledge. KBLaM works with a knowledge base (KB) constructed from a corpus of documents, transforming each piece of knowledge in the KB into continuous key-value vector pairs via pre-trained sentence encoders with linear adapters and integrating them into pre-trained LLMs via a specialized rectangular attention mechanism. Unlike Retrieval-Augmented Generation, KBLaM eliminates external retrieval modules, and unlike in-context learning, its computational overhead scales linearly with KB size rather than quadratically. Our approach enables integrating a large KB of more than 10K triples into an 8B pre-trained LLM of only 8K context window on one single A100 80GB GPU and allows for dynamic updates without model fine-tuning or retraining. Experiments demonstrate KBLaM's effectiveness in various tasks, including question-answering and open-ended reasoning, while providing interpretable insights into its use of the augmented knowledge.}, url = {http://approjects.co.za/?big=en-us/research/publication/kblam-knowledge-base-augmented-language-model-2/}, }