UniProbe: A Learnable Token-Level Hallucination Detector for Large VLMs using Multi-Structural Internal Representations

• URL: http://arxiv.org/abs/2608.10835v1
• Date: Tue, 11 Aug 2026 12:01:59 GMT
• Title: UniProbe: A Learnable Token-Level Hallucination Detector for Large VLMs using Multi-Structural Internal Representations
• Abstract summary: Large Vision-Language Models (LVLMs) achieve impressive visual reasoning and dialogue capabilities, yet frequently hallucinate content unsupported by the visual input.<n>We introduce textbfUniProbe, a lightweight, unified, learnable detector that models a frozen LVLM's heterogeneous computational trace from a single forward pass.
• Score: 61.85916280854257
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Large Vision-Language Models (LVLMs) achieve impressive visual reasoning and dialogue capabilities, yet frequently hallucinate content unsupported by the visual input. Effective mitigation requires token-level localization, enabling targeted intervention without discarding the entire response. Existing detectors require expensive full-model fine-tuning, rely on external verifiers that ignore the model's generation process, or reduce internal signals to isolated features and hand-crafted statistics, discarding spatial, sequential, and relational structure. We introduce \textbf{UniProbe}, a lightweight, unified, learnable detector that models a frozen LVLM's heterogeneous computational trace from a single forward pass. UniProbe constructs a directed graph over image patches, query tokens, and generated tokens, with attention weights encoding their relations. It processes this trace with alternating structure-aware modules: a GNN for relational evidence, a ViT for 2-D visual geometry, and a GRU for response order. Interleaving them allows spatial, relational, and sequential evidence to interact throughout the detector. We further develop a streaming variant for hallucination-aware decoding, which detects and resamples hallucinated tokens during generation, and a self-adaptation strategy aligning the detector with the LVLM's own generations. Across diverse LVLM backbones, UniProbe achieves state-of-the-art token-level and object-hallucination detection. During decoding, it reduces object hallucinations by up to 55\% at $1.06\times$ the latency of standard generation.

Related papers

• Mixture-of-Expert Blocks Contain Strong Hallucination Detection Signals [2.2302915692528367]
  We introduce InnerExpert, the first method to leverage MoE-specific signals for per-token hallucination detection.<n>Our results show that InnerExpert outperforms existing methods across five datasets and two MoE architectures.
  arXiv  Detail & Related papers  (2026-08-18T12:00:20Z)
• DeMTS: Denoising Trajectories as Multivariate Time Series for Hallucination Detection in Diffusion Language Models [59.414664850109155]
  Diffusion large language models (D-LLMs) have emerged as a promising paradigm for text generation.<n>D-LLMs remain vulnerable to hallucinations, where fluent outputs may contain factually incorrect or unsupported content.
  arXiv  Detail & Related papers  (2026-07-24T06:45:43Z)
• Transcoders Trace Visual Grounding and Hallucinations in Vision-Language Models [7.425292797106273]
  Generative Vision-Language Models (VLMs) perform well on multimodal reasoning, but how visual inputs are transformed to text remains poorly understood.<n>We adopt a function-centric framework based on Transcoders, sparse approximations of sublayers that act as a causal proxy for layer-wise.<n>We show that function-centric circuit decomposition yields interpretable and predictive accounts of multimodal computation inVLMs.
  arXiv  Detail & Related papers  (2026-05-21T17:34:39Z)
• Look Carefully: Adaptive Visual Reinforcements in Multimodal Large Language Models for Hallucination Mitigation [51.743225614196774]
  Multimodal large language models (MLLMs) have achieved remarkable progress in vision-language reasoning.<n>They remain vulnerable to hallucination, where generated content deviates from visual evidence.<n>Recent vision enhancement methods attempt to address this issue by reinforcing visual tokens during decoding.<n>We propose Adaptive Visual Reinforcement (AIR), a training-free framework for MLLMs.
  arXiv  Detail & Related papers  (2026-02-27T14:18:51Z)
• Hyperdimensional Probe: Decoding LLM Representations via Vector Symbolic Architectures [12.466522376751811]
  Hyperdimensional Probe is a novel paradigm for decoding information from the Large Language Models vector space.<n>It combines ideas from symbolic representations and neural probing to project the model's residual stream into interpretable concepts.<n>Our work advances information decoding in LLM vector space, enabling extracting more informative, interpretable, and structured features from neural representations.
  arXiv  Detail & Related papers  (2025-09-29T16:59:07Z)
• Generate, but Verify: Reducing Hallucination in Vision-Language Models with Retrospective Resampling [78.78822033285938]
  Vision-Language Models (VLMs) excel at visual understanding but often suffer from visual hallucinations.<n>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)
• Exploring Causes and Mitigation of Hallucinations in Large Vision Language Models [24.241691571850403]
  Large Vision-Language Models (LVLMs) integrate image encoders with Large Language Models (LLMs) to process multi-modal inputs and perform complex visual tasks.<n>They often generate hallucinations by describing non-existent objects or attributes, compromising their reliability.<n>This study analyzes hallucination patterns in image captioning, showing that not all tokens in the generation process are influenced by image input.
  arXiv  Detail & Related papers  (2025-02-24T05:00:52Z)
• Self-Correcting Decoding with Generative Feedback for Mitigating Hallucinations in Large Vision-Language Models [65.4610281589017]
  Large Vision-Language Models (LVLMs) are prone to generating hallucinatory text responses that do not align with the given visual input.<n>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 Object Hallucination via Concentric Causal Attention [71.27325347912823]
  We show that object hallucination is closely tied with Rotary Position. RoPE, a widely adopted positional dependency modeling design. We propose Concentric Causal Attention (CCA), a simple yet effective positional alignment strategy.
  arXiv  Detail & Related papers  (2024-10-21T11:54:53Z)
• Seeing is Believing: Mitigating Hallucination in Large Vision-Language Models via CLIP-Guided Decoding [36.81476620057058]
  Large Vision-Language Models (LVLMs) are susceptible to object hallucinations. Current approaches often rely on the model's token likelihoods or other internal information. We introduce our CLIP-Guided Decoding approach to reduce object hallucination at decoding time.
  arXiv  Detail & Related papers  (2024-02-23T12:57:16Z)

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.