paper-with-me

Papers

KAM-CoT: Knowledge Augmented Multimodal Chain-of-Thoughts Reasoning

2024-01-23 · Debjyoti Mondal, Suraj Modi, Subhadarshi Panda, Rituraj Singh, Godawari Sudhakar Rao

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.

📄 PDF Abstract BibTeX arXiv:2401.12863

Code (0)

등록된 구현이 없습니다.

Tasks

Knowledge Graphs

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
15 Ways to Contact How can i speak to someone at Delta Airlines 설명 없음
Attention 설명 없음
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Similar Papers 제목 키워드 기반

Visual Abstract Thinking Empowers Multimodal Reasoning

2025-05-26 · Dairu Liu, Ziyue Wang, Minyuan Ruan, Fuwen Luo 외

Images usually convey richer detail than text, but often include redundant information which potentially downgrades multimodal reasoning performance. When faced with lengthy or complex messages, humans tend to employ abs…

Multimodal ReasoningRelational ReasoningVisual Reasoning

Visual Thoughts: A Unified Perspective of Understanding Multimodal Chain-of-Thought

2025-05-21 · Zihui Cheng, Qiguang Chen, Xiao Xu, Jiaqi Wang 외

Large Vision-Language Models (LVLMs) have achieved significant success in multimodal tasks, with multimodal chain-of-thought (MCoT) further enhancing performance and interpretability. Recent MCoT methods fall into two ca…

ThinkMorph: Emergent Properties in Multimodal Interleaved Chain-of-Thought Reasoning

2025-10-30 · Jiawei Gu, Yunzhuo Hao, Huichen Will Wang, Linjie Li 외 arxiv

Multimodal reasoning requires iterative coordination between language and vision, yet it remains unclear what constitutes a meaningful interleaved chain of thought. We posit that text and image thoughts should function a…

Multimodal Reasoning

RAT: Retrieval Augmented Thoughts Elicit Context-Aware Reasoning in Long-Horizon Generation

2024-03-08 · ZiHao Wang, Anji Liu, Haowei Lin, Jiaqi Li 외

We explore how iterative revising a chain of thoughts with the help of information retrieval significantly improves large language models' reasoning and generation ability in long-horizon generation tasks, while hugely m…

Code GenerationHallucinationInformation RetrievalMathematical Reasoning+2

GAMBIT: A Gamified Jailbreak Framework for Multimodal Large Language Models

2026-01-06 · Xiangdong Hu, Yangyang Jiang, Qin Hu, Xiaojun Jia arxiv

Multimodal Large Language Models (MLLMs) have become widely deployed, yet their safety alignment remains fragile under adversarial inputs. Previous work has shown that increasing inference steps can disrupt safety mechan…