Chain-of-Description: What I can understand, I can put into words
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929726434574336 |
|---|---|
| author | Guo, Jiaxin Wei, Daimeng Li, Zongyao Shang, Hengchao Luo, Yuanchang Yang, Hao |
| author_facet | Guo, Jiaxin Wei, Daimeng Li, Zongyao Shang, Hengchao Luo, Yuanchang Yang, Hao |
| contents | In this paper, we propose a novel strategy defined as Chain-of-Description (CoD) Prompting, tailored for Multi-Modal Large Language Models. This approach involves having the model first provide a detailed description of the multi-modal input before generating an answer to the question. When applied to models such as Qwen2-Audio, Qwen2-VL, and Qwen2.5-VL, CoD Prompting significantly enhances performance compared to standard prompting methods. This is demonstrated by nearly a 4\% improvement in the speech category of the audio benchmark AIR-Bench-Chat and a 5.3\% improvement in the hard-level portion of the vision benchmark MMMU\_Pro. Our ablation study further validates the effectiveness of CoD Prompting. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_16137 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Chain-of-Description: What I can understand, I can put into words Guo, Jiaxin Wei, Daimeng Li, Zongyao Shang, Hengchao Luo, Yuanchang Yang, Hao Computation and Language Artificial Intelligence In this paper, we propose a novel strategy defined as Chain-of-Description (CoD) Prompting, tailored for Multi-Modal Large Language Models. This approach involves having the model first provide a detailed description of the multi-modal input before generating an answer to the question. When applied to models such as Qwen2-Audio, Qwen2-VL, and Qwen2.5-VL, CoD Prompting significantly enhances performance compared to standard prompting methods. This is demonstrated by nearly a 4\% improvement in the speech category of the audio benchmark AIR-Bench-Chat and a 5.3\% improvement in the hard-level portion of the vision benchmark MMMU\_Pro. Our ablation study further validates the effectiveness of CoD Prompting. |
| title | Chain-of-Description: What I can understand, I can put into words |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2502.16137 |