# Grounded Chain-of-Thought for Multimodal Large Language Models Source: [Grounded Chain-of-Thought for Multimodal Large Language Models]() Collection index: [llms.txt]() Data updated: 2025-10-27T06:49:55.154Z Authors: Qiong Wu, Xiangcong Yang, Yiyi Zhou, Chenxin Fang, Baiyang Song, Xiaoshuai Sun, Rongrong Ji Published: 2025-03-17T04:07:47.000Z ## Abstract Despite great progress, existing multimodal large language models (MLLMs) are prone to visual hallucination, greatly impeding their trustworthy applications. In this paper, we study this problem from the perspective of visual-spatial reasoning, and propose a new learning task for MLLMs, termed Grounded Chain-of-Thought (GCoT). Different from recent visual CoT studies, which focus more on visual knowledge reasoning, GCoT is keen to helping MLLMs to recognize and ground the relevant visual cues step by step, thereby predicting the correct answer with grounding coordinates as the intuitive basis. To facilitate this task, we also carefully design and construct a dataset called multimodal grounded chain-of-thought (MM-GCoT) consisting of 24,022 GCoT examples for 5,033 images. Besides, a comprehensive consistency evaluation system is also introduced, including the metrics of answer accuracy, grounding accuracy and answer-grounding consistency. We further design and conduct a bunch of experiments on 12 advanced MLLMs, and reveal some notable findings: i. most MLLMs performs poorly on the consistency evaluation, indicating obvious visual hallucination; ii. visual hallucination is not directly related to the parameter size and general multimodal performance, i.e., a larger and stronger MLLM is not less affected by this issue. Lastly, we also demonstrate that the proposed dataset can help existing MLLMs to well cultivate their GCoT capability and reduce the inconsistent answering significantly. Moreover, their GCoT can be also generalized to exiting multimodal tasks, such as open-world QA and REC. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Grounded Reasoning on MM-GCoT](): Grounded Reasoning; MM-GCoT; Attribute Accuracy (A-Acc): 74.7. ## Original sources and implementation [Original paper]() [PDF]()