AlignGPT: Multi-modal Large Language Models with Adaptive Alignment Capability

23 May 2024  ·  Fei Zhao, Taotian Pang, Chunhui Li, Zhen Wu, Junjie Guo, Shangyu Xing, Xinyu Dai ·

Multimodal Large Language Models (MLLMs) are widely regarded as crucial in the exploration of Artificial General Intelligence (AGI). The core of MLLMs lies in their capability to achieve cross-modal alignment. To attain this goal, current MLLMs typically follow a two-phase training paradigm: the pre-training phase and the instruction-tuning phase. Despite their success, there are shortcomings in the modeling of alignment capabilities within these models. Firstly, during the pre-training phase, the model usually assumes that all image-text pairs are uniformly aligned, but in fact the degree of alignment between different image-text pairs is inconsistent. Secondly, the instructions currently used for finetuning incorporate a variety of tasks, different tasks's instructions usually require different levels of alignment capabilities, but previous MLLMs overlook these differentiated alignment needs. To tackle these issues, we propose a new multimodal large language model AlignGPT. In the pre-training stage, instead of treating all image-text pairs equally, we assign different levels of alignment capabilities to different image-text pairs. Then, in the instruction-tuning phase, we adaptively combine these different levels of alignment capabilities to meet the dynamic alignment needs of different instructions. Extensive experimental results show that our model achieves competitive performance on 12 benchmarks.

PDF Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Benchmark
Visual Question Answering MM-Vet AlignGPT (Vicuna-7B) GPT-4 score 30.8 # 99
Visual Question Answering MM-Vet AlignGPT (Vicuna-13B) GPT-4 score 35.6 # 74

Methods


No methods listed for this paper. Add relevant methods here