Socratic Questioning: Learn to Self-guide Multimodal Reasoning in the Wild

• URL: http://arxiv.org/abs/2501.02964v2
• Date: Tue, 07 Jan 2025 02:55:15 GMT
• Title: Socratic Questioning: Learn to Self-guide Multimodal Reasoning in the Wild
• Authors: Wanpeng Hu, Haodi Liu, Lin Chen, Feng Zhou, Changming Xiao, Qi Yang, Changshui Zhang,
• Abstract summary: We devise an innovative training and reasoning framework suitable for lightweight Multimodal Large Language Models (MLLMs) Our self-questioning approach organically guides MLLMs to focus on visual clues relevant to the target problem, reducing hallucinations and enhancing the model's ability to describe fine-grained image details. Our experiments on various benchmarks demonstrate SQ's remarkable capabilities in self-questioning, zero-shot visual reasoning and hallucination mitigation.
• Score: 35.91285472401222
• License:
• Abstract: Complex visual reasoning remains a key challenge today. Typically, the challenge is tackled using methodologies such as Chain of Thought (COT) and visual instruction tuning. However, how to organically combine these two methodologies for greater success remains unexplored. Also, issues like hallucinations and high training cost still need to be addressed. In this work, we devise an innovative multi-round training and reasoning framework suitable for lightweight Multimodal Large Language Models (MLLMs). Our self-questioning approach heuristically guides MLLMs to focus on visual clues relevant to the target problem, reducing hallucinations and enhancing the model's ability to describe fine-grained image details. This ultimately enables the model to perform well in complex visual reasoning and question-answering tasks. We have named this framework Socratic Questioning(SQ). To facilitate future research, we create a multimodal mini-dataset named CapQA, which includes 1k images of fine-grained activities, for visual instruction tuning and evaluation, our proposed SQ method leads to a 31.2% improvement in the hallucination score. Our extensive experiments on various benchmarks demonstrate SQ's remarkable capabilities in heuristic self-questioning, zero-shot visual reasoning and hallucination mitigation. Our model and code will be publicly available.

Related papers

• DRIVINGVQA: Analyzing Visual Chain-of-Thought Reasoning of Vision Language Models in Real-World Scenarios with Driving Theory Tests [69.00444996464662]
  We present DrivingVQA, a new benchmark derived from driving theory tests to evaluate visual chain-of-thought reasoning in complex real-world scenarios. Our experiments reveal that open-source and proprietary LVLMs struggle with visual chain-of-thought reasoning under zero-shot settings. We investigate training strategies that leverage relevant entities to improve visual reasoning.
  arXiv  Detail & Related papers  (2025-01-08T18:31:16Z)
• Enhancing Visual Reasoning with Autonomous Imagination in Multimodal Large Language Models [27.78471707423076]
  We propose a new visual reasoning paradigm enabling MLLMs to autonomously modify the input scene to new ones based on its reasoning status. We introduce a novel plug-and-play imagination space, where MLLMs conduct visual modifications through operations like focus, ignore, and transform. We validate our approach through a benchmark spanning dense counting, simple jigsaw puzzle solving, and object placement.
  arXiv  Detail & Related papers  (2024-11-27T08:44:25Z)
• Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination [13.706325901731665]
  Multimodal large language models (MLLMs) have advanced the integration of visual and linguistic modalities. Current approaches like chain of thought (CoT) reasoning have augmented the cognitive capabilities of large language models (LLMs) But their adaptation to MLLMs is hindered by heightened risks of hallucination in cross-modality comprehension.
  arXiv  Detail & Related papers  (2024-11-15T21:01:37Z)
• ProReason: Multi-Modal Proactive Reasoning with Decoupled Eyesight and Wisdom [42.03770972100087]
  We introduce a novel visual reasoning framework named ProReason. ProReason features multi-run proactive perception and decoupled vision-reasoning capabilities. Our experiments demonstrate that ProReason outperforms both existing multi-step reasoning frameworks and passive peer methods.
  arXiv  Detail & Related papers  (2024-10-18T03:22:06Z)
• Explore the Hallucination on Low-level Perception for MLLMs [83.12180878559295]
  We aim to define and evaluate the self-awareness of MLLMs in low-level visual perception and understanding tasks. We present QL-Bench, a benchmark settings to simulate human responses to low-level vision. We demonstrate that while some models exhibit robust low-level visual capabilities, their self-awareness remains relatively underdeveloped.
  arXiv  Detail & Related papers  (2024-09-15T14:38:29Z)
• Eyeballing Combinatorial Problems: A Case Study of Using Multimodal Large Language Models to Solve Traveling Salesman Problems [6.157421830538752]
  Multimodal Large Language Models (MLLMs) have demonstrated proficiency in processing di-verse modalities. This paper investigates the use of MLLMs' visual capabilities to 'eyeball' solutions for the Traveling Salesman Problem.
  arXiv  Detail & Related papers  (2024-06-11T00:41:08Z)
• Cantor: Inspiring Multimodal Chain-of-Thought of MLLM [83.6663322930814]
  We argue that converging visual context acquisition and logical reasoning is pivotal for tackling visual reasoning tasks. We propose an innovative multimodal CoT framework, termed Cantor, characterized by a perception-decision architecture. Our experiments demonstrate the efficacy of the proposed framework, showing significant improvements in multimodal CoT performance.
  arXiv  Detail & Related papers  (2024-04-24T17:59:48Z)
• Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs [50.77984109941538]
  Our research reveals that the visual capabilities in recent multimodal LLMs still exhibit systematic shortcomings. We identify ''CLIP-blind pairs'' - images that CLIP perceives as similar despite their clear visual differences. We evaluate various CLIP-based vision-and-language models and found a notable correlation between visual patterns that challenge CLIP models and those problematic for multimodal LLMs.
  arXiv  Detail & Related papers  (2024-01-11T18:58:36Z)
• Good Questions Help Zero-Shot Image Reasoning [110.1671684828904]
  Question-Driven Visual Exploration (QVix) is a novel prompting strategy that enhances the exploratory capabilities of large vision-language models (LVLMs) QVix enables a wider exploration of visual scenes, improving the LVLMs' reasoning accuracy and depth in tasks such as visual question answering and visual entailment. Our evaluations on various challenging zero-shot vision-language benchmarks, including ScienceQA and fine-grained visual classification, demonstrate that QVix significantly outperforms existing methods.
  arXiv  Detail & Related papers  (2023-12-04T03:18:51Z)

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.