mlsanityData to 14 Oct 2026

VisER: Visual Evidence and Reliance for Object Hallucination Detection in LVLMs

arXiv 2608.30480 ↗First posted 31 Aug 2026cs.CV cs.LGcited by 0

On the map: Multimodal LLMs / vision-language models → Hallucination mitigation in LVLMs

Abstract (arXiv)

Object hallucination remains a persistent reliability issue in large vision-language models, where generated object mentions may sound plausible but lack visual grounding. Recent training-free detectors use internal signals such as token likelihood, attention, visual confidence, or image-text similarity to identify hallucinated objects. These signals are useful, but they are often source-confounded. They measure how strongly an object is supported inside the model without distinguishing whether that support comes from object-specific visual evidence or the generated text prefix. In difficult cases, a hallucinated object can still receive high internal support because it fits the scene, is associated with nearby visual cues, or follows naturally from the generated text prefix. We propose VisER, a training-free two-sided metric for object-level hallucination detection. VisER evaluates each generated object mention from two complementary views. Visual Evidence measures whether object-context compatibility is backed by object-specific evidence from image tokens. Visual Reliance measures whether the object is supported more by the image than by the generated prefix. Combining these views gives a more source-aware grounding score, while avoiding additional object-level verification generations. Across multiple LVLMs and benchmarks, VisER improves AUROC and AUPR over a range of baselines.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Hallucination mitigation in LVLMs, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 17 of its 28 references that are in the map. First posted on arXiv 31 Aug 2026.

Builds on

17 of 28 references.

Closest ancestors · 11

Same direction, newest first

  1. 2025GLSim: Detecting Object Hallucinations in LVLMs via Global-Local Similarity27 Aug
  2. 2025Hallucinatory Image Tokens: A Training-free EAZY Approach on Detecting and Mitigating Object Hallucinations in LVLMs10 Mar
  3. 2024Beyond Logit Lens: Contextual Embeddings for Robust Hallucination Detection & Grounding in VLMs28 Nov
  4. 2024Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens23 Nov
  5. 2024DAMRO: Dive into the Attention Mechanism of LVLM to Reduce Object Hallucination6 Oct
  6. 2024Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations3 Oct
  7. 2024Paying More Attention to Image: A Training-Free Method for Alleviating Hallucination in LVLMs31 Jul
  8. 2024Detecting and Mitigating Hallucination in Large Vision Language Models via Fine-Grained AI Feedback22 Apr
  9. 2023OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocation29 Nov
  10. 2023Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding28 Nov
  11. 2023Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning26 Jun

Other references · 6

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  2. 2023Improved Baselines with Visual Instruction Tuningcited by 4,418
  3. 2023InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuningcited by 2,876
  4. 2019Attention is not Explanationcited by 929
  5. 2023Aligning Large Multimodal Models with Factually Augmented RLHFcited by 712
  6. 2024ALOHa: A New Measure for Hallucination in Captioning Modelscited by 45

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Hallucinations Leave a Grounding Signature:Verifier-Guided Decoding for Selective Object Correction
  2. 2026Beyond the Global Scores: Fine-Grained Token Grounding as a Robust Detector of LVLM Hallucinations
  3. 2026TruthLens: Object Hallucination Detection via Self-Evaluating Truthfulness Scores in LVLMs
  4. 2023Analyzing and Mitigating Object Hallucination in Large Vision-Language Models
  5. 2026DO-Bench: An Attributable Benchmark for Diagnosing Object Hallucination in Vision-Language Models
  6. 2025Seeing is Believing: Rich-Context Hallucination Detection for MLLMs via Backward Visual Grounding
  7. 2026Reducing Object Hallucination in LVLMs via Emphasizing Image-negative Tokens
  8. 2024Logical Closed Loop: Uncovering Object Hallucinations in Large Vision-Language Models