mlsanityData to 7 Oct 2026

Mask What Matters: Mitigating Object Hallucinations in Multimodal Large Language Models with Object-Aligned Visual Contrastive Decoding

arXiv 2602.11737 ↗First posted 12 Feb 2026cs.CV cs.CLcited by 3

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

Abstract (arXiv)

We study object hallucination in Multimodal Large Language Models (MLLMs) and improve visual contrastive decoding (VCD) by constructing an object-aligned auxiliary view. We leverage object-centric attention in self-supervised Vision Transformers. In particular, we remove the most salient visual evidence to construct an auxiliary view that disrupts unsupported tokens and produces a stronger contrast signal. Our method is prompt-agnostic, model-agnostic, and can be seamlessly plugged into the existing VCD pipeline with little computation overhead, i.e., a single cacheable forward pass. Empirically, our method demonstrates consistent gains on two popular object hallucination benchmarks across two MLLMs.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Placed in Hallucination mitigation in LVLMs, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 10 of its 31 references that are in the map. First posted on arXiv 12 Feb 2026.

Builds on

10 of 31 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024Mitigating Object Hallucinations in Large Vision-Language Models with Assembly of Global and Local Attention18 Jun
  2. 2024CODE: Contrasting Self-generated Description to Combat Hallucination in Large Multi-modal Models4 Jun
  3. 2023Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding28 Nov

Other references · 7

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  3. 2023Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyondcited by 2,179
  4. 2022A-OKVQA: A Benchmark for Visual Question Answering using World Knowledgecited by 702
  5. 2018Object Hallucination in Image Captioningcited by 661
  6. 2026Plasticity vs. Rigidity: The Impact of Low-Rank Adapters on Reasoning on a Micro-Budgetcited by 1
  7. 2026Different Time, Different Language: Revisiting the Bias Against Non-Native Speakers in GPT Detectorscited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Instruction-Evidence Contrastive Dual-Stream Decoding for Grounded Vision-Language Reasoningcited by 1
  2. 2026Do We Really Need External Tools to Mitigate Hallucinations? SIRA: Shared-Prefix Internal Reconstruction of Attributioncited by 1
  3. 2026Diagnosing and Mitigating Perception-Decision Misalignment in Omni-LLMs via Modality Subspace Activationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2022Plausible May Not Be Faithful: Probing Object Hallucination in Vision-Language Pre-training
  2. 2026NoLan: Mitigating Object Hallucinations in Large Vision-Language Models via Dynamic Suppression of Language Priors
  3. 2025SECOND: Mitigating Perceptual Hallucination in Vision-Language Models via Selective and Contrastive Decoding
  4. 2026SDCD: Structure-Disrupted Contrastive Decoding for Mitigating Hallucinations in Large Vision-Language Models
  5. 2025ClearSight: Visual Signal Enhancement for Object Hallucination Mitigation in Multimodal Large language Models
  6. 2026Rethinking CD: A Reproducibility Study and Extension on the Ineffectiveness of Contrastive Decoding at Mitigating Object Hallucinations in MLLMs
  7. 2023Evaluating Object Hallucination in Large Vision-Language Models
  8. 2025Watch Closely: Mitigating Object Hallucinations in Large Vision-Language Models with Disentangled Decoding