Pith. sign in

REVIEW 6 cited by

IllusionVQA: A Challenging Optical Illusion Dataset for Vision Language Models

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2403.15952 v3 pith:HIQT5CKM submitted 2024-03-23 cs.CV cs.CL

classification cs.CVcs.CL
keywords comprehensionlocalizationvlmslanguageopticaltaskaccuracychain-of-thought
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

The advent of Vision Language Models (VLM) has allowed researchers to investigate the visual understanding of a neural network using natural language. Beyond object classification and detection, VLMs are capable of visual comprehension and common-sense reasoning. This naturally led to the question: How do VLMs respond when the image itself is inherently unreasonable? To this end, we present IllusionVQA: a diverse dataset of challenging optical illusions and hard-to-interpret scenes to test the capability of VLMs in two distinct multiple-choice VQA tasks - comprehension and soft localization. GPT4V, the best performing VLM, achieves 62.99% accuracy (4-shot) on the comprehension task and 49.7% on the localization task (4-shot and Chain-of-Thought). Human evaluation reveals that humans achieve 91.03% and 100% accuracy in comprehension and localization. We discover that In-Context Learning (ICL) and Chain-of-Thought reasoning substantially degrade the performance of Gemini-Pro in the localization task. Tangentially, we discover a potential weakness in the ICL capabilities of VLMs: they fail to locate optical illusions even when the correct answer is in the context window as a few-shot example.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. MVI-Bench: A Comprehensive Benchmark for Evaluating Robustness to Misleading Visual Inputs in LVLMs

    cs.CV 2025-11 unverdicted novelty 8.0 of 10

    MVI-Bench supplies the first taxonomy and dataset focused on misleading visual inputs to measure LVLM robustness, with tests on 18 models revealing clear weaknesses.

  2. Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions

    cs.CR 2025-07 conditional novelty 7.0 of 10

    Hateful optical illusions generated with Stable Diffusion and ControlNet evade current moderation classifiers (best accuracy 0.245) and vision-language models (best accuracy 0.102), with simple image transformations s...

  3. Pattern over Pixels: Measuring Pattern Completion Bias in Multimodal Code Generation

    cs.SE 2026-08 conditional novelty 6.0 of 10

    On a new 1,440-screenshot fill-in-the-blank benchmark, five frontier multimodal models default to repeated UI patterns instead of visual deviations, with mean bias rates from 69.8% on card widths to 80.2% on font sizes.

  4. SMSP: A Plug-and-Play Strategy of Multi-Scale Perception for MLLMs to Perceive Visual Illusions

    cs.CV 2026-03 conditional novelty 6.0 of 10

    SMSP, a plug-and-play multi-scale low-pass preprocessing method, lets MLLMs recognize hidden characters in visual illusions by reducing high-frequency background distraction.

  5. Do Large Vision-Language Models Distinguish between the Actual and Apparent Features of Illusions?

    cs.CV 2025-06 conditional novelty 6.0 of 10

    Large vision-language models that appear to recognize visual illusions often answer fake-illusion questions from prior knowledge, not from actually seeing the images.

  6. Empowering Multimodal LLMs with External Tools: A Comprehensive Survey

    cs.CV 2025-08 unverdicted novelty 2.0 of 10

    A survey paper maps how external tools are used to augment multimodal large language models across data, tasks, evaluation, and future directions.

Pith tools