English

Dynamic Knowledge Integration for Enhanced Vision-Language Reasoning

Computation and Language 2025-01-16 v1

Abstract

Large Vision-Language Models (LVLMs) have demonstrated impressive capabilities in multimodal tasks, but their performance is often constrained by the lack of external knowledge integration, limiting their ability to handle knowledge-intensive tasks such as visual question answering and reasoning. To address this challenge, we propose a novel method, Adaptive Knowledge-Guided Pretraining for Large Vision-Language Models (AKGP-LVLM), which dynamically incorporates structured and unstructured knowledge into LVLMs during pretraining and fine-tuning. Our approach employs a knowledge encoder to represent external knowledge, a retrieval mechanism to select task-relevant information, and a dynamic adaptor to align multimodal and knowledge representations effectively. We evaluate our method on four benchmark datasets, demonstrating significant performance improvements over state-of-the-art models. Furthermore, human evaluations highlight the superior correctness and relevance of our model's outputs. Extensive analyses confirm the robustness, efficiency, and scalability of AKGP-LVLM, making it a compelling solution for real-world knowledge-intensive tasks.

Keywords

Cite

@article{arxiv.2501.08597,
  title  = {Dynamic Knowledge Integration for Enhanced Vision-Language Reasoning},
  author = {Julian Perry and Surasakdi Siripong and Thanakorn Phonchai},
  journal= {arXiv preprint arXiv:2501.08597},
  year   = {2025}
}
R2 v1 2026-06-28T21:06:47.743Z