The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering

• URL: http://arxiv.org/abs/2502.03628v1
• Date: Wed, 05 Feb 2025 21:34:02 GMT
• Title: The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering
• Authors: Zhuowei Li, Haizhou Shi, Yunhe Gao, Di Liu, Zhenting Wang, Yuxiao Chen, Ting Liu, Long Zhao, Hao Wang, Dimitris N. Metaxas,
• Abstract summary: We investigate the internal dynamics of hallucination by examining the tokens logits rankings throughout the generation process.<n>We propose VISTA, a training-free inference-time intervention framework that reduces hallucination while promoting genuine information.
• Score: 42.09744951074433
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Vision-Language Models (LVLMs) can reason effectively over both textual and visual inputs, but they tend to hallucinate syntactically coherent yet visually ungrounded contents. In this paper, we investigate the internal dynamics of hallucination by examining the tokens logits rankings throughout the generation process, revealing three key patterns in how LVLMs process information: (1) gradual visual information loss -- visually grounded tokens gradually become less favored throughout generation, and (2) early excitation -- semantically meaningful tokens achieve peak activation in the layers earlier than the final layer. (3) hidden genuine information -- visually grounded tokens though not being eventually decided still retain relatively high rankings at inference. Based on these insights, we propose VISTA (Visual Information Steering with Token-logit Augmentation), a training-free inference-time intervention framework that reduces hallucination while promoting genuine information. VISTA works by combining two complementary approaches: reinforcing visual information in activation space and leveraging early layer activations to promote semantically meaningful decoding. Compared to existing methods, VISTA requires no external supervision and is applicable to various decoding strategies. Extensive experiments show that VISTA on average reduces hallucination by abount 40% on evaluated open-ended generation task, and it consistently outperforms existing methods on four benchmarks across four architectures under three decoding strategies.

Related papers

• Generate, but Verify: Reducing Hallucination in Vision-Language Models with Retrospective Resampling [67.14942827452161]
  Vision-Language Models (VLMs) excel at visual understanding but often suffer from visual hallucinations. In this work, we introduce REVERSE, a unified framework that integrates hallucination-aware training with on-the-fly self-verification.
  arXiv  Detail & Related papers  (2025-04-17T17:59:22Z)
• Text Speaks Louder than Vision: ASCII Art Reveals Textual Biases in Vision-Language Models [93.46875303598577]
  Vision-language models (VLMs) have advanced rapidly in processing multimodal information, but their ability to reconcile conflicting signals remains underexplored. This work investigates how VLMs process ASCII art, a unique medium where textual elements collectively form visual patterns, potentially creating semantic-visual conflicts.
  arXiv  Detail & Related papers  (2025-04-02T10:47:07Z)
• Lifting the Veil on Visual Information Flow in MLLMs: Unlocking Pathways to Faster Inference [28.24397677839652]
  Multimodal large language models (MLLMs) improve performance on vision-language tasks by integrating visual features from pre-trained vision encoders into large language models. How MLLMs process and utilize visual information remains unclear. We propose Hierarchical Modality-Aware Pruning (HiMAP), a plug-and-play inference acceleration method that dynamically prunes image tokens at specific layers, reducing computational costs by approximately 65% without sacrificing performance.
  arXiv  Detail & Related papers  (2025-03-17T12:31:23Z)
• Fixing Imbalanced Attention to Mitigate In-Context Hallucination of Large Vision-Language Model [0.0]
  Large Vision Language Models (LVLMs) have demonstrated remarkable capabilities in understanding and describing visual content.<n>These models frequently exhibit hallucination behavior, where they generate descriptions containing objects or details absent in the input image.<n>We propose a novel attention modification approach that combines selective token emphasis and head-specific modulation to maintain visual grounding.
  arXiv  Detail & Related papers  (2025-01-21T15:22:31Z)
• FiVL: A Framework for Improved Vision-Language Alignment through the Lens of Training, Evaluation and Explainability [10.184567639685321]
  We introduce FiVL, a novel method for constructing datasets designed to train LVLMs for enhanced visual grounding. We present benchmarks to assess the model's ability to use image as substantive evidence. We identify attention heads with the strongest vision-language alignment, enabling explainability on visual-driven hallucinations.
  arXiv  Detail & Related papers  (2024-12-19T09:24:10Z)
• 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)<n>We introduce Vision-aware Head Divergence (VHD), a metric that quantifies the sensitivity of attention head outputs to visual context.<n>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)
• VaLiD: Mitigating the Hallucination of Large Vision Language Models by Visual Layer Fusion Contrastive Decoding [38.23310445372371]
  Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities in multimodal task reasoning. 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 to mitigate hallucinations by adjusting the decoding strategy during the inference stage. We propose a novel hallucination-mitigation method from the visual encoding perspective: textbfVisutextbfal textbfLayer Fustextbfion Contrastive textbfD
  arXiv  Detail & Related papers  (2024-11-24T13:42:02Z)
• Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens [7.806633929976787]
  Hallucinations in Large Vision-Language Models (LVLMs) significantly undermine their reliability.<n>This paper addresses how LVLMs process visual information and whether this process causes hallucination.<n>We propose a simple inference-time method that adjusts visual attention by integrating information across various heads.
  arXiv  Detail & Related papers  (2024-11-23T03:40:05Z)
• Self-Introspective Decoding: Alleviating Hallucinations for Large Vision-Language Models [30.26685485474035]
  Large Vision-Language Models (LVLMs) have rapidly advanced in recent years. The prevalent issue known as the hallucination' problem has emerged as a significant bottleneck. We propose a simple yet effective method named Self-Introspective Decoding (SID)
  arXiv  Detail & Related papers  (2024-08-04T13:50:17Z)
• Attend and Enrich: Enhanced Visual Prompt for Zero-Shot Learning [114.59476118365266]
  We propose AENet, which endows semantic information into the visual prompt to distill semantic-enhanced prompt for visual representation enrichment.<n> AENet comprises two key steps: 1) exploring the concept-harmonized tokens for the visual and attribute modalities, grounded on the modal-sharing token that represents consistent visual-semantic concepts; and 2) yielding semantic-enhanced prompt via the visual residual refinement unit with attribute consistency supervision.
  arXiv  Detail & Related papers  (2024-06-05T07:59:48Z)
• DiMBERT: Learning Vision-Language Grounded Representations with Disentangled Multimodal-Attention [101.99313208598569]
  Vision-and-language (V-L) tasks require the system to understand both vision content and natural language. We propose DiMBERT (short for Disentangled Multimodal-Attention BERT), which applies separated attention spaces for vision and language. We show that DiMBERT sets new state-of-the-art performance on three tasks.
  arXiv  Detail & Related papers  (2022-10-28T23:00:40Z)
• A Simple Long-Tailed Recognition Baseline via Vision-Language Model [92.2866546058082]
  The visual world naturally exhibits a long-tailed distribution of open classes, which poses great challenges to modern visual systems. Recent advances in contrastive visual-language pretraining shed light on a new pathway for visual recognition. We propose BALLAD to leverage contrastive vision-language models for long-tailed recognition.
  arXiv  Detail & Related papers  (2021-11-29T17:49:24Z)

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.