VaLiD: Mitigating the Hallucination of Large Vision Language Models by Visual Layer Fusion Contrastive Decoding
- URL: http://arxiv.org/abs/2411.15839v1
- Date: Sun, 24 Nov 2024 13:42:02 GMT
- Title: VaLiD: Mitigating the Hallucination of Large Vision Language Models by Visual Layer Fusion Contrastive Decoding
- Authors: Jiaqi Wang, Yifei Gao, Jitao Sang,
- Abstract summary: Large Vision-Language Models (LVLMs) have demonstrated outstanding performance in multimodal task reasoning.
We propose a novel hallucination-mitigation method from the visual encoding perspective: textbfVisutextbfal textbfLayer Fustextbfion Contrastive textbfDecoding (VaLiD)
- Score: 38.23310445372371
- License:
- Abstract: Large Vision-Language Models (LVLMs) have demonstrated outstanding performance in multimodal task reasoning. However, they often generate responses that appear plausible yet do not accurately reflect the visual content, a phenomenon known as hallucination. Recent approaches have introduced training-free methods that mitigate hallucinations by adjusting the decoding strategy during inference stage, typically attributing hallucination to the language model itself. Our analysis, however, reveals that distortions in the visual encoding process significantly affect the model's reasoning accuracy. Specifically, earlier visual layers may retain key features but gradually distort as the information propagates toward the output layer. Building on these findings, we propose a novel hallucination-mitigation method from the visual encoding perspective: \textbf{V}isu\textbf{a}l \textbf{L}ayer Fus\textbf{i}on Contrastive \textbf{D}ecoding (VaLiD). This method utilizes uncertainty to guide the selection of visual hidden layers, correcting distortions in the visual encoding process and thereby improving the reliability of generated text. Experimental results show that VaLiD effectively reduces hallucinations across various benchmarks, achieving state-of-the-art performance compared to multiple baseline methods.
Related papers
- Self-Correcting Decoding with Generative Feedback for Mitigating Hallucinations in Large Vision-Language Models [66.71616369573715]
Large Vision-Language Models (LVLMs) are prone to generating hallucinatory text responses that do not align with the given visual input.
We introduce self-correcting Decoding with Generative Feedback (DeGF), a novel training-free algorithm that incorporates feedback from text-to-image generative models into the decoding process.
arXiv Detail & Related papers (2025-02-10T03:43:55Z) - Mitigating Hallucination for Large Vision Language Model by Inter-Modality Correlation Calibration Decoding [66.06337890279839]
Large vision-language models (LVLMs) have shown remarkable capabilities in visual-language understanding for downstream multi-modal tasks.
LVLMs still suffer from generating hallucinations in complex generation tasks, leading to inconsistencies between visual inputs and generated content.
We propose an Inter-Modality Correlation Decoding (IMCCD) method to mitigate hallucinations in LVLMs in a training-free manner.
arXiv Detail & Related papers (2025-01-03T17:56:28Z) - Cracking the Code of Hallucination in LVLMs with Vision-aware Head Divergence [69.86946427928511]
We investigate the internal mechanisms driving hallucination in large vision-language models (LVLMs)
We introduce Vision-aware Head Divergence (VHD), a metric that quantifies the sensitivity of attention head outputs to visual context.
We propose Vision-aware Head Reinforcement (VHR), a training-free approach to mitigate hallucination by enhancing the role of vision-aware attention heads.
arXiv Detail & Related papers (2024-12-18T15:29:30Z) - Delve into Visual Contrastive Decoding for Hallucination Mitigation of Large Vision-Language Models [40.70957762776874]
Large vision-language models (LVLMs) have shown impressive capabilities in generating plausible responses correlated with input visual contents.
They still suffer from hallucinations, where the generated text inaccurately reflects visual contents.
Recent approaches apply contrastive decoding to calibrate the model's response via contrasting output distributions with original and visually distorted samples.
arXiv Detail & Related papers (2024-12-09T18:57:57Z) - CATCH: Complementary Adaptive Token-level Contrastive Decoding to Mitigate Hallucinations in LVLMs [74.36850397755572]
CATCH addresses issues related to visual defects that cause diminished fine-grained feature perception and cumulative hallucinations in open-ended scenarios.
It is applicable to various visual question-answering tasks without requiring any specific data or prior knowledge, and generalizes robustly to new tasks without additional training.
arXiv Detail & Related papers (2024-11-19T18:27:31Z) - Alleviating Hallucinations in Large Vision-Language Models through Hallucination-Induced Optimization [123.54980913741828]
Large Visual Language Models (LVLMs) have demonstrated exceptional abilities in understanding multimodal data.
They invariably suffer from hallucinations, leading to a disconnect between the generated text and the corresponding images.
Almost all current visual contrastive decoding methods attempt to mitigate these hallucinations by introducing visual uncertainty information.
However, they struggle to precisely induce the hallucinatory tokens, which severely limits their effectiveness in mitigating hallucinations.
arXiv Detail & Related papers (2024-05-24T08:46:31Z) - Mitigating Hallucinations in Large Vision-Language Models with Instruction Contrastive Decoding [25.489832294197797]
This paper introduces the Instruction Contrastive Decoding (ICD) method, a novel approach designed to reduce hallucinations during LVLM inference.
Our method is inspired by our observation that what we call disturbance instructions significantly exacerbate hallucinations in multimodal fusion modules.
arXiv Detail & Related papers (2024-03-27T16:04:47Z) - IBD: Alleviating Hallucinations in Large Vision-Language Models via
Image-Biased Decoding [37.16880672402059]
Over-reliance on linguistic priors has been identified as a key factor leading to hallucinations.
We propose to alleviate this problem by introducing a novel image-biased decoding technique.
Our method derives the next-token probability distribution by contrasting predictions from a conventional LVLM with those of an image-biased LVLM.
arXiv Detail & Related papers (2024-02-28T16:57:22Z) - Mitigating Object Hallucinations in Large Vision-Language Models through
Visual Contrastive Decoding [125.05295513481035]
We introduce Visual Contrastive Decoding (VCD), a simple and training-free method that contrasts output distributions derived from original and distorted visual inputs.
The proposed VCD effectively reduces the over-reliance on statistical bias and unimodal priors, two essential causes of object hallucinations.
Our experiments show that VCD, without either additional training or the usage of external tools, significantly mitigates the object hallucination issue across different LVLM families.
arXiv Detail & Related papers (2023-11-28T16:26:35Z)
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.