Illusion-Aware Visual Preprocessing and Anti-Illusion Prompting for Classic Illusion Understanding in Vision-Language Models
On the map: Multimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
Abstract (arXiv)
Vision-Language Models (VLMs) exhibit systematic bias toward visual illusions, recalling memorized facts rather than perceiving actual visual differences. This paper presents a training-free framework for the 5th DataCV Challenge Task 1 at CVPR 2026, addressing this perception-versus-memory conflict through three complementary strategies:(1) illusion-aware image preprocessing that weakens illusion-inducing context via type-specific transformations (edge extraction, color isolation, morphological processing, and reference-line overlay), (2) anti-illusion prompt engineering guiding VLMs toward qualitative visual comparison, and (3) multi-vote ensemble that further improves robustness. Our method achieves 90.48% accuracy on the official 630-image test set using Claude (claude-opus-4-6) with 5-vote majority ensemble, and 98.41% on a human-verified subset. The approach requires no finetuning, relying solely on visual manipulation and prompt design. Our solution secured 2nd place in the challenge, only 0.47% behind the 1st-place solution. Code is available at https://github.com/jasminezz/sf-illusion-aware-vlm.git.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in VLM benchmarks and visual reasoning, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 11 of its 21 references that are in the map. First posted on arXiv 9 May 2026.
Builds on
11 of 21 references.
Closest ancestors · 5
Same direction, newest first
- 2026Seeing Is Believing? A Benchmark for Multimodal Large Language Models on Visual Illusions and Anomalies2 Feb
- 2026Do VLMs Perceive or Recall? Probing Visual Perception vs. Memory with Classic Visual Illusions29 Jan
- 2024CogVLM2: Visual Language Models for Image and Video Understanding29 Aug
- 2024IllusionVQA: A Challenging Optical Illusion Dataset for Vision Language Models23 Mar
- 2022Flamingo: a Visual Language Model for Few-Shot Learning29 Apr
Other references · 6
- 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
- 2023Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decodingcited by 671
- 2023HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Modelscited by 572
- 2024A Survey on Hallucination in Large Vision-Language Modelscited by 352
- 2024Illusory VQA: Benchmarking and Enhancing Multimodal Models on Visual Illusionscited by 10
- 2025Increasing LLM response trustworthiness using voting ensemblescited by 1
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026Seeing the Evidence, Missing the Answer: Tool-Guided Vision-Language Models on Visual Illusions
- 2025IllusionBench+: A Large-scale and Comprehensive Benchmark for Visual Illusion Understanding in Vision-Language Models
- 2025SemVink: Advancing VLMs' Semantic Understanding of Optical Illusions via Visual Global Thinking
- 2026Beyond Shortcuts: Mitigating Visual Illusions in Frozen VLMs via Qualitative Reasoning
- 2026Can LVLMs Uncover the Truth Behind Visual Illusions? An Analysis of Perceptual and Reasoning Capabilities
- 2026SMSP: A Plug-and-Play Strategy of Multi-Scale Perception for MLLMs to Perceive Visual Illusions
- 2025Do Large Vision-Language Models Distinguish between the Actual and Apparent Features of Illusions?
- 2024Evaluating Model Perception of Color Illusions in Photorealistic Scenes