Bootstrapping Grounded Chain-of-Thought in Multimodal LLMs for Data-Efficient Model Adaptation
By: Jiaer Xia , Bingkui Tong , Yuhang Zang and more
Potential Business Impact:
Teaches computers to understand charts and tables better.
Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in interpreting images using natural language. However, without using large-scale datasets for retraining, these models are difficult to adapt to specialized vision tasks, e.g., chart understanding. This problem is caused by a mismatch between pre-training and downstream datasets: pre-training datasets primarily concentrate on scenes and objects but contain limited information about specialized, non-object images, such as charts and tables. In this paper, we share an interesting finding that training an MLLM with Chain-of-Thought (CoT) reasoning data can facilitate model adaptation in specialized vision tasks, especially under data-limited regimes. However, we identify a critical issue within CoT data distilled from pre-trained MLLMs, i.e., the data often contains multiple factual errors in the reasoning steps. To address the problem, we propose Grounded Chain-of-Thought (GCoT), a simple bootstrapping-based approach that aims to inject grounding information (i.e., bounding boxes) into CoT data, essentially making the reasoning steps more faithful to input images. We evaluate our approach on five specialized vision tasks, which cover a variety of visual formats including charts, tables, receipts, and reports. The results demonstrate that under data-limited regimes our approach significantly improves upon fine-tuning and distillation.
Similar Papers
Grounded Chain-of-Thought for Multimodal Large Language Models
CV and Pattern Recognition
Makes AI understand pictures without making things up.
From Perception to Reasoning: Deep Thinking Empowers Multimodal Large Language Models
Computation and Language
Helps AI "think step-by-step" to solve harder problems.
From Perception to Reasoning: Deep Thinking Empowers Multimodal Large Language Models
Computation and Language
Helps AI "think" step-by-step to solve harder problems.