Enhance Reasoning Ability of Visual-Language Models via Large Language Models
This addresses a specific limitation in VLMs for tasks requiring reasoning, but it is incremental as it builds on existing models without introducing a new paradigm.
The authors tackled the insufficient reasoning ability of visual-language models (VLMs) by proposing TReE, a method that transfers reasoning capabilities from large language models (LLMs) to VLMs in zero-shot scenarios, resulting in enhanced performance on reasoning tasks.
Pre-trained visual language models (VLM) have shown excellent performance in image caption tasks. However, it sometimes shows insufficient reasoning ability. In contrast, large language models (LLMs) emerge with powerful reasoning capabilities. Therefore, we propose a method called TReE, which transfers the reasoning ability of a large language model to a visual language model in zero-shot scenarios. TReE contains three stages: observation, thinking, and re-thinking. Observation stage indicates that VLM obtains the overall information of the relative image. Thinking stage combines the image information and task description as the prompt of the LLM, inference with the rationals. Re-Thinking stage learns from rationale and then inference the final result through VLM.