Grounded Chain-of-Thought for Multimodal Large Language Models

• URL: http://arxiv.org/abs/2503.12799v2
• Date: Mon, 24 Mar 2025 11:30:58 GMT
• Title: Grounded Chain-of-Thought for Multimodal Large Language Models
• Authors: Qiong Wu, Xiangcong Yang, Yiyi Zhou, Chenxin Fang, Baiyang Song, Xiaoshuai Sun, Rongrong Ji,
• Abstract summary: We propose a new learning task for multimodal large language models (MLLMs) called Grounded Chain-of-Thought (GCoT)<n>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.<n>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.
• Score: 66.04061083611863
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• VOILA: Evaluation of MLLMs For Perceptual Understanding and Analogical Reasoning [63.0285363282581]
  Multimodal Large Language Models (MLLMs) have become a powerful tool for integrating visual and textual information.<n>We introduce VOILA, a benchmark designed to evaluate MLLMs' perceptual understanding and abstract relational reasoning.<n>We reveal that current MLLMs struggle to comprehend inter-image relationships and exhibit limited capabilities in high-level relational reasoning.
  arXiv  Detail & Related papers  (2025-02-25T23:36:19Z)
• MLLMs Know Where to Look: Training-free Perception of Small Visual Details with Multimodal LLMs [11.532430076027554]
  We study whether MLLMs can perceive small visual details as effectively as large ones when answering questions about images. We propose training-free visual intervention methods that leverage the internal knowledge of any MLLM itself.
  arXiv  Detail & Related papers  (2025-02-24T18:54:40Z)
• VisFactor: Benchmarking Fundamental Visual Cognition in Multimodal Large Language Models [62.667142971664575]
  We introduce VisFactor, a novel benchmark derived from the Factor-Referenced Cognitive Test (FRCT)<n>VisFactor digitalizes vision-related FRCT subtests to systematically evaluate MLLMs across essential visual cognitive tasks.<n>We present a comprehensive evaluation of state-of-the-art MLLMs, such as GPT-4o, Gemini-Pro, and Qwen-VL.
  arXiv  Detail & Related papers  (2025-02-23T04:21:32Z)
• Visual RAG: Expanding MLLM visual knowledge without fine-tuning [5.341192792319891]
  This paper introduces Visual RAG, that synergically combines the MLLMs capability to learn from the context, with a retrieval mechanism.<n>In this way, the resulting system is not limited to the knowledge extracted from the training data, but can be updated rapidly and easily without fine-tuning.<n>It greatly reduces the computational costs for improving the model image classification performance, and augments the model knowledge to new visual domains and tasks it was not trained for.
  arXiv  Detail & Related papers  (2025-01-18T17:43:05Z)
• Open Eyes, Then Reason: Fine-grained Visual Mathematical Understanding in MLLMs [62.875934732547435]
  Current large language models (MLLMs) often underperform on mathematical problem-solving tasks that require fine-grained visual understanding. In this paper, we evaluate the visual grounding capabilities of state-of-the-art MLLMs and reveal a significant negative correlation between visual grounding accuracy and problem-solving performance. We propose a novel approach, SVE-Math, featuring a geometric-grounded vision encoder and a feature router that dynamically adjusts the contribution of hierarchical visual feature maps.
  arXiv  Detail & Related papers  (2025-01-11T04:08:44Z)
• Accelerating Multimodal Large Language Models via Dynamic Visual-Token Exit and the Empirical Findings [69.35226485836641]
  Excessive use of visual tokens in existing Multimoal Large Language Models (MLLMs) often exhibits obvious redundancy and brings in prohibitively expensive computation. We propose a simple yet effective method to improve the efficiency of MLLMs, termed dynamic visual-token exit (DyVTE) DyVTE uses lightweight hyper-networks to perceive the text token status and decide the removal of all visual tokens after a certain layer.
  arXiv  Detail & Related papers  (2024-11-29T11:24:23Z)
• Rethinking VLMs and LLMs for Image Classification [6.550471260627169]
  Large Language Models (LLMs) are increasingly being merged with Visual Language Models (VLMs) to enable new capabilities. We show that, for object and scene recognition, VLMs that do not leverage LLMs can achieve better performance than VLMs that do. We propose a pragmatic solution: a lightweight fix involving a relatively small LLM that efficiently routes visual tasks to the most suitable model for the task.
  arXiv  Detail & Related papers  (2024-10-03T23:40:21Z)
• Visual CoT: Advancing Multi-Modal Language Models with a Comprehensive Dataset and Benchmark for Chain-of-Thought Reasoning [40.972648044298374]
  Multi-Modal Large Language Models (MLLMs) have demonstrated impressive performance in various VQA tasks. They often lack interpretability and struggle with complex visual inputs. We introduce the large-scale Visual CoT dataset comprising 438k question-answer pairs. We propose a multi-turn processing pipeline that dynamically focuses on visual inputs and provides interpretable thoughts.
  arXiv  Detail & Related papers  (2024-03-25T17:59:23Z)
• Behind the Magic, MERLIM: Multi-modal Evaluation Benchmark for Large Image-Language Models [50.653838482083614]
  This paper introduces a scalable test-bed to assess the capabilities of IT-LVLMs on fundamental computer vision tasks. MERLIM contains over 300K image-question pairs and has a strong focus on detecting cross-modal "hallucination" events in IT-LVLMs.
  arXiv  Detail & Related papers  (2023-12-03T16:39:36Z)
• From CLIP to DINO: Visual Encoders Shout in Multi-modal Large Language Models [36.41816380074965]
  We investigate the effectiveness of different vision encoders within Large Language Models (MLLMs) Our findings reveal that the shallow layer features of CLIP offer particular advantages for fine-grained tasks such as grounding and region understanding. We propose a simple yet effective feature merging strategy, named COMM, that integrates CLIP and DINO with Multi-level features Merging.
  arXiv  Detail & Related papers  (2023-10-13T02:41:55Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.