Referring Expression Comprehension and Segmentation are critical tasks for assessing the integration of language understanding and image comprehension, serving as benchmarks for Multimodal Large Language Models (MLLMs) capabilities. To address these challenges, we propose a new strategy, CoT Referring, which enhances model reasoning across modalities through a structured, chain-of-thought training data structure. Our approach systematically parses textual structures to a sequential referring step, where in each step it identifies relationships and ensures consistent reference alignment, thereby improving accuracy in complex query scenarios. We restructure the training data to enforce a new output form, providing new annotations for existing datasets and compiling an evaluation benchmark from existing resources. This benchmark is designed explicitly for complex referring cases. We also integrate detection and segmentation capabilities into a unified MLLM framework, training it with a novel adaptive weighted loss to optimize performance. Experimental results on our curated benchmark and RefCOCO/+/g demonstrate the effectiveness of our approach, with a notable increase of 2.5%+ over baseline models.
@article{arxiv.2510.06243,
title = {CoT Referring: Improving Referring Expression Tasks with Grounded Reasoning},
author = {Qihua Dong and Luis Figueroa and Handong Zhao and Kushal Kafle and Jason Kuen and Zhihong Ding and Scott Cohen and Yun Fu},
journal= {arXiv preprint arXiv:2510.06243},
year = {2026}
}