KORE: Enhancing Knowledge Injection for Large Multimodal Models via Knowledge-Oriented Controls

TL;DR

KORE is a novel method that enhances knowledge injection in large multimodal models by enabling effective learning of new information while preserving existing knowledge, addressing limitations of previous approaches.

Contribution

KORE introduces structured knowledge augmentation and covariance-based retention mechanisms for improved knowledge injection in large multimodal models.

Findings

KORE outperforms existing methods in new knowledge injection tasks.

KORE effectively mitigates catastrophic forgetting in large multimodal models.

Experiments on multiple models demonstrate KORE's superior performance.

Abstract

Large Multimodal Models encode extensive factual knowledge in their pre-trained weights. However, its knowledge remains static and limited, unable to keep pace with real-world developments, which hinders continuous knowledge acquisition. Effective knowledge injection thus becomes critical, involving two goals: knowledge adaptation (injecting new knowledge) and knowledge retention (preserving old knowledge). Existing methods often struggle to learn new knowledge and suffer from catastrophic forgetting. To address this, we propose KORE, a synergistic method of KnOwledge-oRientEd augmentations and constraints for injecting new knowledge into large multimodal models while preserving old knowledge. Unlike general text or image data augmentation, KORE automatically converts individual knowledge items into structured and comprehensive knowledge to ensure that the model accurately learns new knowledge, enabling accurate adaptation. Meanwhile, KORE stores previous knowledge in the covariance matrix of LMM's linear layer activations and initializes the adapter by projecting the original weights into the matrix's null space, defining a fine-tuning direction that minimizes interference with previous knowledge, enabling powerful retention. Extensive experiments on various LMMs, including LLaVA-v1.5-7B, LLaVA-v1.5-13B, and Qwen2.5-VL-7B, show that KORE achieves superior new knowledge injection performance and effectively mitigates catastrophic forgetting.