InfuserKI: Enhancing Large Language Models with Knowledge Graphs via Infuser-Guided Knowledge Integration
This addresses a data inefficiency issue in knowledge integration for LLMs, which is incremental as it builds on existing methods to prevent knowledge forgetting.
The paper tackles the problem of efficiently integrating unknown knowledge into large language models without causing forgetting of existing knowledge, achieving reductions in knowledge forgetting of 9% and 6% on two domain knowledge graphs.
Large Language Models (LLMs) have achieved exceptional capabilities in open generation across various domains, yet they encounter difficulties with tasks that require intensive knowledge. To address these challenges, methods for integrating knowledge have been developed, which augment LLMs with domain-specific knowledge graphs through external modules. These approaches, however, face data inefficiency issues as they necessitate the processing of both known and unknown knowledge for fine-tuning. Thus, our research focuses on a novel problem: efficiently integrating unknown knowledge into LLMs without unnecessary overlap of known knowledge. A risk of introducing new knowledge is the potential forgetting of existing knowledge. To mitigate this risk, we propose the innovative {\method} framework. This framework employs transformer internal states to determine when to enrich LLM outputs with additional information, effectively preventing knowledge forgetting. Performance evaluations using the UMLS-2.5k and MetaQA domain knowledge graphs reveal that {\method} not only successfully integrates new knowledge but also outperforms state-of-the-art baselines, reducing knowledge forgetting by 9\% and 6\%, respectively.