Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zheng, Haojie, Xu, Tianyang, Sun, Hanchi, Pu, Shu, Chen, Ruoxi, Sun, Lichao
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909395760185344
author Zheng, Haojie
Xu, Tianyang
Sun, Hanchi
Pu, Shu
Chen, Ruoxi
Sun, Lichao
author_facet Zheng, Haojie
Xu, Tianyang
Sun, Hanchi
Pu, Shu
Chen, Ruoxi
Sun, Lichao
contents Multimodal large language models (MLLMs) have advanced the integration of visual and linguistic modalities, establishing themselves as the dominant paradigm for visual-language tasks. Current approaches like chain of thought (CoT) reasoning have augmented the cognitive capabilities of large language models (LLMs), yet their adaptation to MLLMs is hindered by heightened risks of hallucination in cross-modality comprehension. In this paper, we find that the thinking while looking paradigm in current multimodal CoT approaches--where reasoning chains are generated alongside visual input--fails to mitigate hallucinations caused by misleading images. To address these limitations, we propose the Visual Inference Chain (VIC) framework, a novel approach that constructs reasoning chains using textual context alone before introducing visual input, effectively reducing cross-modal biases and enhancing multimodal reasoning accuracy. Comprehensive evaluations demonstrate that VIC significantly improves zero-shot performance across various vision-related tasks, mitigating hallucinations while refining the reasoning capabilities of MLLMs. Our code repository can be found at https://github.com/Terry-Xu-666/visual_inference_chain.
format Preprint
id arxiv_https___arxiv_org_abs_2411_12591
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination
Zheng, Haojie
Xu, Tianyang
Sun, Hanchi
Pu, Shu
Chen, Ruoxi
Sun, Lichao
Computer Vision and Pattern Recognition
Artificial Intelligence
Multimodal large language models (MLLMs) have advanced the integration of visual and linguistic modalities, establishing themselves as the dominant paradigm for visual-language tasks. Current approaches like chain of thought (CoT) reasoning have augmented the cognitive capabilities of large language models (LLMs), yet their adaptation to MLLMs is hindered by heightened risks of hallucination in cross-modality comprehension. In this paper, we find that the thinking while looking paradigm in current multimodal CoT approaches--where reasoning chains are generated alongside visual input--fails to mitigate hallucinations caused by misleading images. To address these limitations, we propose the Visual Inference Chain (VIC) framework, a novel approach that constructs reasoning chains using textual context alone before introducing visual input, effectively reducing cross-modal biases and enhancing multimodal reasoning accuracy. Comprehensive evaluations demonstrate that VIC significantly improves zero-shot performance across various vision-related tasks, mitigating hallucinations while refining the reasoning capabilities of MLLMs. Our code repository can be found at https://github.com/Terry-Xu-666/visual_inference_chain.
title Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2411.12591