EnsemHalDet: Robust VLM Hallucination Detection via Ensemble of Internal State Detectors

• URL: http://arxiv.org/abs/2604.02784v1
• Date: Fri, 03 Apr 2026 06:48:27 GMT
• Title: EnsemHalDet: Robust VLM Hallucination Detection via Ensemble of Internal State Detectors
• Abstract summary: Vision-Language Models (VLMs) excel at multimodal tasks, but they remain vulnerable to hallucinations that are factually incorrect or ungrounded in the input image.<n>Recent work suggests that hallucination detection using internal representations is more efficient and accurate than approaches that rely solely on model outputs.<n>We propose EnsemHalDet, an ensemble-based hallucination detection framework.
• Score: 1.4401311275746886
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Vision-Language Models (VLMs) excel at multimodal tasks, but they remain vulnerable to hallucinations that are factually incorrect or ungrounded in the input image. Recent work suggests that hallucination detection using internal representations is more efficient and accurate than approaches that rely solely on model outputs. However, existing internal-representation-based methods typically rely on a single representation or detector, limiting their ability to capture diverse hallucination signals. In this paper, we propose EnsemHalDet, an ensemble-based hallucination detection framework that leverages multiple internal representations of VLMs, including attention outputs and hidden states. EnsemHalDet trains independent detectors for each representation and combines them through ensemble learning. Experimental results across multiple VQA datasets and VLMs show that EnsemHalDet consistently outperforms prior methods and single-detector models in terms of AUC. These results demonstrate that ensembling diverse internal signals significantly improves robustness in multimodal hallucination detection.

Related papers

• UniProbe: A Learnable Token-Level Hallucination Detector for Large VLMs using Multi-Structural Internal Representations [61.85916280854257]
  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.
  arXiv  Detail & Related papers  (2026-08-11T12:01:59Z)
• Beyond Global Editing: Per-Instance Disentangled Subspaces for Training-Free Hallucination Mitigation in LVLMs [16.83614016603383]
  We propose a training-free hallucination mitigation framework for large vision-language models.<n>Our method first constructs a set of Disentangled Hallucination Subspaces, each isolating a distinct hallucination mode.<n>Experiments across multiple vision-language benchmarks and LVLM families demonstrate consistent improvements.
  arXiv  Detail & Related papers  (2026-08-10T09:21:12Z)
• 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)
• VCE: A zero-cost hallucination mitigation method of LVLMs via visual contrastive editing [70.82867621856968]
  Large vision-language models (LVLMs) frequently suffer from Object Hallucination (OH)<n>Recent studies suggest that the hallucination problem may stem from language priors.<n>We propose Visual Contrastive Editing (VCE), a novel post-hoc method that identifies and suppresses hallucinatory tendencies.
  arXiv  Detail & Related papers  (2026-04-21T12:40:07Z)
• Learning Uncertainty from Sequential Internal Dispersion in Large Language Models [52.29267172760918]
  Uncertainty estimation is a promising approach to detect hallucinations in large language models.<n>Recent approaches commonly depend on model internal states to estimate uncertainty.<n>We present Sequential Internal Variance Representation (SIVR), a supervised hallucination detection framework.
  arXiv  Detail & Related papers  (2026-04-17T06:31:29Z)
• Revealing and Enhancing Core Visual Regions: Harnessing Internal Attention Dynamics for Hallucination Mitigation in LVLMs [67.69730908817321]
  Internal Positive Attention Dynamics (PAD) in LVLMs naturally reveal semantically core visual regions under the distortions of attention sinks.<n>We propose Positive Attention Dynamics Enhancement (PADE), a training-free attention intervention that constructs a PAD map to identify semantically core visual regions.
  arXiv  Detail & Related papers  (2026-02-17T13:08:06Z)
• Zero-shot HOI Detection with MLLM-based Detector-agnostic Interaction Recognition [71.5328300638085]
  Zero-shot Human-object interaction (HOI) detection aims to locate humans and objects in images and recognize their interactions.<n>Existing methods, including two-stage methods, tightly couple interaction recognition with a specific detector.<n>We propose a decoupled framework that separates object detection from IR and leverages multi-modal large language models (MLLMs) for zero-shot IR.
  arXiv  Detail & Related papers  (2026-02-16T19:01:31Z)
• FaithSCAN: Model-Driven Single-Pass Hallucination Detection for Faithful Visual Question Answering [14.550872089352943]
  FaithSCAN is a lightweight network that detects hallucinations by exploiting rich internal signals of vision-language models.<n>We extend the LLM-as-a-Judge paradigm to VQA hallucination and propose a low-cost strategy to automatically generate model-dependent supervision signals.<n>In-depth analysis shows hallucinations arise from systematic internal state variations in visual perception, cross-modal reasoning, and language decoding.
  arXiv  Detail & Related papers  (2026-01-01T09:19:39Z)
• TraceDet: Hallucination Detection from the Decoding Trace of Diffusion Large Language Models [49.83690850047884]
  hallucination problem in D-LLMs remains underexplored, limiting their reliability in real-world applications.<n>Existing hallucination detection methods are designed for AR-LLMs and rely on signals from single-step generation.<n>We propose TraceDet, a novel framework that explicitly leverages the intermediate denoising steps of D-LLMs for hallucination detection.
  arXiv  Detail & Related papers  (2025-09-30T02:01:10Z)
• HIDE and Seek: Detecting Hallucinations in Language Models via Decoupled Representations [17.673293240849787]
  Contemporary Language Models (LMs) often generate content that is factually incorrect or unfaithful to the input context.<n>We propose a single-pass, training-free approach for effective Hallucination detectIon via Decoupled rEpresentations (HIDE)<n>Our results demonstrate that HIDE outperforms other single-pass methods in almost all settings.
  arXiv  Detail & Related papers  (2025-06-21T16:02:49Z)
• 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)
• Robust Hallucination Detection in LLMs via Adaptive Token Selection [35.06045656558144]
  Hallucinations in large language models (LLMs) pose significant safety concerns that impede their broader deployment.<n>We propose HaMI, a novel approach that enables robust detection of hallucinations through adaptive selection and learning of critical tokens.<n>We achieve this robustness by an innovative formulation of the Hallucination detection task as Multiple Instance (HaMI) learning over token-level representations within a sequence.
  arXiv  Detail & Related papers  (2025-04-10T15:39:10Z)
• AutoHall: Automated Hallucination Dataset Generation for Large Language Models [56.92068213969036]
  This paper introduces a method for automatically constructing model-specific hallucination datasets based on existing fact-checking datasets called AutoHall. We also propose a zero-resource and black-box hallucination detection method based on self-contradiction.
  arXiv  Detail & Related papers  (2023-09-30T05:20:02Z)

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.