Mitigating Hallucination in Large Vision-Language Models via Adaptive Attention Calibration

• URL: http://arxiv.org/abs/2505.21472v1
• Date: Tue, 27 May 2025 17:45:21 GMT
• Title: Mitigating Hallucination in Large Vision-Language Models via Adaptive Attention Calibration
• Authors: Mehrdad Fazli, Bowen Wei, Ziwei Zhu,
• Abstract summary: Large vision-language models (LVLMs) achieve impressive performance on multimodal tasks but often suffer from hallucination.<n>We introduce the Confidence-Aware Attention framework to address this challenge.
• Score: 1.7373859011890633
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large vision-language models (LVLMs) achieve impressive performance on multimodal tasks but often suffer from hallucination, and confidently describe objects or attributes not present in the image. Current inference-time interventions, while training-free, struggle to maintain accuracy in open-ended and long-form generation scenarios. We introduce the Confidence-Aware Attention Calibration (CAAC) framework to address this challenge by targeting two key biases: spatial perception bias, which distributes attention disproportionately across image tokens, and modality bias, which shifts focus from visual to textual inputs over time. CAAC employs a two-step approach: Visual-Token Calibration (VTC) to balance attention across visual tokens, and Adaptive Attention Re-Scaling (AAR) to reinforce visual grounding based on the model's confidence. This confidence-driven adjustment ensures consistent visual alignment during generation. Experiments on CHAIR, AMBER, and POPE benchmarks demonstrate that CAAC outperforms baselines, particularly in long-form generations, effectively reducing hallucination.

Related papers

• Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation [46.3194503355054]
  Large vision-language models (LVLMs) have shown remarkable capabilities across a wide range of multimodal tasks.<n>They remain prone to visual hallucination (VH), often producing confident but incorrect descriptions of visual content.<n>We present VisFlow, an efficient and training-free framework designed to mitigate VH by directly manipulating attention patterns during inference.
  arXiv  Detail & Related papers  (2025-06-14T19:10:22Z)
• Gaze-Guided Learning: Avoiding Shortcut Bias in Visual Classification [3.1208151315473622]
  We introduce Gaze-CIFAR-10, a human gaze time-series dataset, along with a dual-sequence gaze encoder.<n>In parallel, a Vision Transformer (ViT) is employed to learn the sequential representation of image content.<n>Our framework integrates human gaze priors with machine-derived visual sequences, effectively correcting inaccurate localization in image feature representations.
  arXiv  Detail & Related papers  (2025-04-08T00:40:46Z)
• Multi-Cue Adaptive Visual Token Pruning for Large Vision-Language Models [85.51753014478315]
  We introduce AdaptPrune, a novel plug-and-play training-free pruning method.<n>It builds on conventional attention-based pruning by integrating spatial distance and token similarity with an adaptive NMS approach.<n>Our approach ensures a comprehensive evaluation of token importance and substantially refines the pruning decisions.
  arXiv  Detail & Related papers  (2025-03-11T03:58:17Z)
• Mitigating Object Hallucinations in Large Vision-Language Models via Attention Calibration [22.39558434131574]
  Large Vision-Language Models (LVLMs) generate responses that are not factually aligned with the visual content.<n>We introduce a training-free solution, Uniform Attention (UAC), that estimates the bias from single meaningless input image.<n>We also introduce a fine-tuning solution, Dynamic Attention (DAC), that enforces the consistent outputs wherever the object locates in the image.
  arXiv  Detail & Related papers  (2025-02-04T03:27:38Z)
• PAINT: Paying Attention to INformed Tokens to Mitigate Hallucination in Large Vision-Language Model [0.0]
  hallucinations often arise from the progressive weakening of attention weight to visual tokens.<n>textbfPAINT (textbfPaying textbfAttention to textbfINformed textbfTokens) is a plug-and-play framework that intervenes in the self-attention mechanism of the Large Vision Language Models.
  arXiv  Detail & Related papers  (2025-01-21T15:22:31Z)
• 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.<n>LVLMs still suffer from generating hallucinations in complex generation tasks, leading to inconsistencies between visual inputs and generated content.<n>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)
• Adaptive Prompt Tuning: Vision Guided Prompt Tuning with Cross-Attention for Fine-Grained Few-Shot Learning [5.242869847419834]
  Few-shot, fine-grained classification in computer vision poses significant challenges due to the need to differentiate subtle class distinctions with limited data.<n>This paper presents a novel method that enhances the Contrastive Language-Image Pre-Training model through adaptive prompt tuning.
  arXiv  Detail & Related papers  (2024-12-19T08:51:01Z)
• 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)
• Don't Miss the Forest for the Trees: Attentional Vision Calibration for Large Vision Language Models [16.185253476874006]
  Large Vision Language Models (LVLMs) demonstrate strong capabilities in visual understanding and description, yet often suffer from hallucinations.<n>We propose Attentional Vision (AvisC), a test-time approach that recalibrates the influence of blind tokens without modifying the underlying attention mechanism.<n>Experiments on standard benchmarks, including POPE, MME, and AMBER, demonstrate that AvisC effectively reduces hallucinations in LVLMs.
  arXiv  Detail & Related papers  (2024-05-28T04:40:57Z)
• Dual-Image Enhanced CLIP for Zero-Shot Anomaly Detection [58.228940066769596]
  We introduce a Dual-Image Enhanced CLIP approach, leveraging a joint vision-language scoring system. Our methods process pairs of images, utilizing each as a visual reference for the other, thereby enriching the inference process with visual context. Our approach significantly exploits the potential of vision-language joint anomaly detection and demonstrates comparable performance with current SOTA methods across various datasets.
  arXiv  Detail & Related papers  (2024-05-08T03:13:20Z)
• More Than Just Attention: Learning Cross-Modal Attentions with Contrastive Constraints [63.08768589044052]
  We propose Contrastive Content Re-sourcing ( CCR) and Contrastive Content Swapping ( CCS) constraints to address such limitation. CCR and CCS constraints supervise the training of attention models in a contrastive learning manner without requiring explicit attention annotations. Experiments on both Flickr30k and MS-COCO datasets demonstrate that integrating these attention constraints into two state-of-the-art attention-based models improves the model performance.
  arXiv  Detail & Related papers  (2021-05-20T08:48:10Z)
• Visual Alignment Constraint for Continuous Sign Language Recognition [74.26707067455837]
  Vision-based Continuous Sign Language Recognition aims to recognize unsegmented gestures from image sequences. In this work, we revisit the overfitting problem in recent CTC-based CSLR works and attribute it to the insufficient training of the feature extractor. We propose a Visual Alignment Constraint (VAC) to enhance the feature extractor with more alignment supervision.
  arXiv  Detail & Related papers  (2021-04-06T07:24:58Z)

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.