OrderChain: Towards General Instruct-Tuning for Stimulating the Ordinal Understanding Ability of MLLM
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_ | 1866915445541437440 |
|---|---|
| author | Wang, Jinhong Tong, Shuo liu, Jian Tang, Dongqi Wang, Weiqiang Li, Wentong Xu, Hongxia Chen, Danny Chen, Jintai Wu, Jian |
| author_facet | Wang, Jinhong Tong, Shuo liu, Jian Tang, Dongqi Wang, Weiqiang Li, Wentong Xu, Hongxia Chen, Danny Chen, Jintai Wu, Jian |
| contents | Despite the remarkable progress of multimodal large language models (MLLMs), they continue to face challenges in achieving competitive performance on ordinal regression (OR; a.k.a. ordinal classification). To address this issue, this paper presents OrderChain, a novel and general prompting paradigm that improves the ordinal understanding ability of MLLMs by specificity and commonality modeling. Specifically, our OrderChain consists of a set of task-aware prompts to facilitate the specificity modeling of diverse OR tasks and a new range optimization Chain-of-Thought (RO-CoT), which learns a commonality way of thinking about OR tasks by uniformly decomposing them into multiple small-range optimization subtasks. Further, we propose a category recursive division (CRD) method to generate instruction candidate category prompts to support RO-CoT automatic optimization. Comprehensive experiments show that LLaVA model with our OrderChain improves baseline LLaVA significantly on diverse OR datasets, e.g., from 47.5\% to 93.2\% accuracy on the Adience dataset for age estimation, and from 30.0\% to 85.7\% accuracy on the Diabetic Retinopathy dataset. Notably, LLaVA with our OrderChain also remarkably outperforms state-of-the-art methods by 27% on accuracy and 0.24 on MAE on the Adience dataset. To our best knowledge, our OrderChain is the first work that augments MLLMs for OR tasks, and the effectiveness is witnessed across a spectrum of OR datasets. Project Page: https://order-chain.github.io/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_04801 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | OrderChain: Towards General Instruct-Tuning for Stimulating the Ordinal Understanding Ability of MLLM Wang, Jinhong Tong, Shuo liu, Jian Tang, Dongqi Wang, Weiqiang Li, Wentong Xu, Hongxia Chen, Danny Chen, Jintai Wu, Jian Computer Vision and Pattern Recognition Despite the remarkable progress of multimodal large language models (MLLMs), they continue to face challenges in achieving competitive performance on ordinal regression (OR; a.k.a. ordinal classification). To address this issue, this paper presents OrderChain, a novel and general prompting paradigm that improves the ordinal understanding ability of MLLMs by specificity and commonality modeling. Specifically, our OrderChain consists of a set of task-aware prompts to facilitate the specificity modeling of diverse OR tasks and a new range optimization Chain-of-Thought (RO-CoT), which learns a commonality way of thinking about OR tasks by uniformly decomposing them into multiple small-range optimization subtasks. Further, we propose a category recursive division (CRD) method to generate instruction candidate category prompts to support RO-CoT automatic optimization. Comprehensive experiments show that LLaVA model with our OrderChain improves baseline LLaVA significantly on diverse OR datasets, e.g., from 47.5\% to 93.2\% accuracy on the Adience dataset for age estimation, and from 30.0\% to 85.7\% accuracy on the Diabetic Retinopathy dataset. Notably, LLaVA with our OrderChain also remarkably outperforms state-of-the-art methods by 27% on accuracy and 0.24 on MAE on the Adience dataset. To our best knowledge, our OrderChain is the first work that augments MLLMs for OR tasks, and the effectiveness is witnessed across a spectrum of OR datasets. Project Page: https://order-chain.github.io/. |
| title | OrderChain: Towards General Instruct-Tuning for Stimulating the Ordinal Understanding Ability of MLLM |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.04801 |