تقرير
KAM-CoT: Knowledge Augmented Multimodal Chain-of-Thoughts Reasoning
العنوان: | KAM-CoT: Knowledge Augmented Multimodal Chain-of-Thoughts Reasoning |
---|---|
المؤلفون: | Mondal, Debjyoti, Modi, Suraj, Panda, Subhadarshi, Singh, Rituraj, Rao, Godawari Sudhakar |
سنة النشر: | 2024 |
المجموعة: | Computer Science |
مصطلحات موضوعية: | Computer Science - Computation and Language, Computer Science - Artificial Intelligence |
الوصف: | Large Language Models (LLMs) have demonstrated impressive performance in natural language processing tasks by leveraging chain of thought (CoT) that enables step-by-step thinking. Extending LLMs with multimodal capabilities is the recent interest, but incurs computational cost and requires substantial hardware resources. To address these challenges, we propose KAM-CoT a framework that integrates CoT reasoning, Knowledge Graphs (KGs), and multiple modalities for a comprehensive understanding of multimodal tasks. KAM-CoT adopts a two-stage training process with KG grounding to generate effective rationales and answers. By incorporating external knowledge from KGs during reasoning, the model gains a deeper contextual understanding reducing hallucinations and enhancing the quality of answers. This knowledge-augmented CoT reasoning empowers the model to handle questions requiring external context, providing more informed answers. Experimental findings show KAM-CoT outperforms the state-of-the-art methods. On the ScienceQA dataset, we achieve an average accuracy of 93.87%, surpassing GPT-3.5 (75.17%) by 18% and GPT-4 (83.99%) by 10%. Remarkably, KAM-CoT achieves these results with only 280M trainable parameters at a time, demonstrating its cost-efficiency and effectiveness. Comment: AAAI 2024 |
نوع الوثيقة: | Working Paper |
URL الوصول: | http://arxiv.org/abs/2401.12863 |
رقم الأكسشن: | edsarx.2401.12863 |
قاعدة البيانات: | arXiv |
الوصف غير متاح. |