Leveraging Visual Signals for Robust Token-Level Uncertainty in Vision-Language Generation

• URL: http://arxiv.org/abs/2605.27136v1
• Date: Tue, 26 May 2026 15:04:55 GMT
• Title: Leveraging Visual Signals for Robust Token-Level Uncertainty in Vision-Language Generation
• Abstract summary: Uncertainty quantification (UQ) remains a critical challenge in Large Vision Language Models (LVLMs)<n>We propose Visual-Grounded Token UQ (VIG-TUQ), a training-free framework that explicitly incorporates visual grounding into uncertainty estimation.
• Score: 10.212763020484092
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Uncertainty quantification (UQ) remains a critical challenge in Large Vision Language Models (LVLMs) for reliable predictions and real-world deployment. However, most existing methods are adapted from the LLM literature and primarily focus on the language modality, leaving the contribution of visual information to LVLM uncertainty largely underexplored. In this paper, we investigate how LVLMs process visual information and whether this process can be used to improve uncertainty estimation. By analyzing hidden representations after the integration of visual features during the generation process, we observe that high-confidence predictions rely more heavily on visual content than uncertain ones. Building on this insight, we propose Visual-Grounded Token UQ (VIG-TUQ), a training-free framework that explicitly incorporates visual grounding into uncertainty estimation by weighting token-level language uncertainty with visual grounding scores. We evaluate VIG-TUQ on multiple datasets and across diverse LVLM architectures, including early-fusion, late-fusion, and native-fusion models. Results indicate that our method often improves upon existing token-level uncertainty approaches. Code and data will be made available upon acceptance.

Related papers

• Benchmarking Large Vision-Language Models on Fine-Grained Image Tasks: From Evaluation to Diagnosis [63.49939245944781]
  We introduce FG-BMK, a comprehensive fine-grained evaluation benchmark containing 1.01 million questions and 0.28 million images.<n>We find that current LVLMs remain inadequate fine-grained recognizers, with failures arising from intertwined bottlenecks in visual representations, semantic grounding, modality alignment, and category-level knowledge.
  arXiv  Detail & Related papers  (2026-06-17T13:23:26Z)
• Diagnosing Visual Ignorance in Vision-Language Models [29.2851901986069]
  Vision-Language Models (VLMs) frequently rely on language priors, producing confident answers that are weakly grounded in visual evidence.<n>In this work, we study language-prior reliance from both mechanistic and behavioral perspectives.<n>We find that language-prior reliance is a systematic routing failure affecting both model internals and benchmark validity.
  arXiv  Detail & Related papers  (2026-06-05T04:16:01Z)
• Uncertainty-Aware Exploratory Direct Preference Optimization for Multimodal Large Language Models [53.15468578562038]
  We propose an Uncertainty-aware Exploratory Direct Preference Optimization (UE-DPO) method for Multimodal Large Language Models (MLLMs)<n>We first quantify the uncertainty from the model's failure to ground token predictions in the given image.<n>We then encourage more learning pressure on visually deficient tokens in preferred samples, and alleviate the over-penalization of beneficial knowledge in dispreferred samples.
  arXiv  Detail & Related papers  (2026-05-06T13:08:12Z)
• Unleashing Vision-Language Semantics for Deepfake Video Detection [78.7562836979696]
  Deepfake Video Detection (DFD) studies have demonstrated that pre-trained Vision-Language Models (VLMs) exhibit strong generalization capabilities in detecting artifacts across different identities.<n>We propose VLAForge, a novel DFD framework that unleashes the potential of such cross-modal semantics to enhance model's discriminability in deepfake detection.
  arXiv  Detail & Related papers  (2026-03-25T16:05:35Z)
• VAUQ: Vision-Aware Uncertainty Quantification for LVLM Self-Evaluation [22.921677603408188]
  Large Vision-Language Models (LVLMs) frequently hallucinate, limiting their safe deployment in real-world applications.<n>We propose VAUQ, a vision-aware uncertainty quantification framework for LVLM self-evaluation.<n>VAUQ explicitly measures how strongly a model's output depends on visual evidence.
  arXiv  Detail & Related papers  (2026-02-24T16:11:14Z)
• Understanding Language Prior of LVLMs by Contrasting Chain-of-Embedding [12.42420657573375]
  We present the first systematic analysis of language prior in large vision-language models (LVLMs)<n>Our analysis reveals a universal phenomenon: each model exhibits a Visual Integration Point (VIP), a critical layer at which visual information begins to meaningfully reshape hidden representations and influence decoding.<n>Across 54 model-dataset combinations spanning 9 contemporary LVLMs and 6 benchmarks, we demonstrate that VIP consistently emerges, and that TVI reliably predicts the strength of language prior.
  arXiv  Detail & Related papers  (2025-09-27T02:12:05Z)
• ViLU: Learning Vision-Language Uncertainties for Failure Prediction [42.22422504877948]
  We introduce ViLU, a new Vision-Language Uncertainty quantification framework.<n>ViLU constructs an uncertainty-aware multi-modal representation by integrating the visual embedding, the predicted textual embedding, and an image-conditioned textual representation via cross-attention.<n>Our proposed approach is well-suited for post-hoc settings, where only vision and text embeddings are available without direct access to the model itself.
  arXiv  Detail & Related papers  (2025-07-10T10:41:13Z)
• Post-hoc Probabilistic Vision-Language Models [54.05237186168399]
  Vision-language models (VLMs) have found remarkable success in classification, retrieval, and generative tasks.<n>We propose post-hoc uncertainty estimation in VLMs that does not require additional training.<n>Our results show promise for safety-critical applications of large-scale models.
  arXiv  Detail & Related papers  (2024-12-08T18:16:13Z)
• Beyond Sight: Towards Cognitive Alignment in LVLM via Enriched Visual Knowledge [24.538839144639653]
  Large Vision-Language Models (LVLMs) integrate separately pre-trained vision and language components. These models frequently encounter a core issue of "cognitive misalignment" between the vision encoder (VE) and the large language model (LLM)
  arXiv  Detail & Related papers  (2024-11-25T18:33:14Z)
• CLUE: Concept-Level Uncertainty Estimation for Large Language Models [49.92690111618016]
  We propose a novel framework for Concept-Level Uncertainty Estimation for Large Language Models (LLMs) We leverage LLMs to convert output sequences into concept-level representations, breaking down sequences into individual concepts and measuring the uncertainty of each concept separately. We conduct experiments to demonstrate that CLUE can provide more interpretable uncertainty estimation results compared with sentence-level uncertainty.
  arXiv  Detail & Related papers  (2024-09-04T18:27:12Z)
• Unconditional Truthfulness: Learning Unconditional Uncertainty of Large Language Models [104.55763564037831]
  We train a regression model that leverages attention maps, probabilities on the current generation step, and recurrently computed uncertainty scores from previously generated tokens.<n>Our evaluation shows that the proposed method is highly effective for selective generation, achieving substantial improvements over rivaling unsupervised and supervised approaches.
  arXiv  Detail & Related papers  (2024-08-20T09:42:26Z)
• Debiasing Multimodal Large Language Models via Penalization of Language Priors [38.97645845493758]
  Multimodal Large Language Models (MLLMs) have become indispensable tools in computer vision and natural language processing.<n>Despite their advancements, our investigation reveals a noteworthy bias: the generated content is often driven more by the inherent priors of the underlying Large Language Models (LLMs) than by the input image.<n>We propose two simple, training-free strategies to rectify these biases and redirect the model's focus toward visual information.
  arXiv  Detail & Related papers  (2024-03-08T12:35:07Z)

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.