# Beyond Shortcuts: Mitigating Visual Illusions in Frozen VLMs via Qualitative Reasoning

arXiv: https://arxiv.org/abs/2604.26250 · HTML: https://mlsanity.com/paper/2604.26250/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 15 of its 18 references that are in the map.
- First posted on arXiv 29 Apr 2026.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)
- Multimodal LLMs / vision-language models / [VLM benchmarks and visual reasoning](https://mlsanity.com/mllm/vlm-benchmarks-and-visual-reasoning/)

## Builds on (most cited first, 15 of 15)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [Evaluating Object Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2305.10355/) (2023)
- [Open-vocabulary Object Detection via Vision and Language Knowledge Distillation](https://mlsanity.com/paper/2104.13921/) (2021)
- [Valley: Video Assistant with Large Language model Enhanced abilitY](https://mlsanity.com/paper/2306.07207/) (2023)
- [Frequency Decoupling for Motion Magnification via Multi-Level Isomorphic Architecture](https://mlsanity.com/paper/2403.07347/) (2024)
- [EulerMormer: Robust Eulerian Motion Magnification via Dynamic Filtering within Transformer](https://mlsanity.com/paper/2312.04152/) (2023)
- [XInsight: Integrative Stage-Consistent Psychological Counseling Support Agents for Digital Well-Being](https://mlsanity.com/paper/2603.06583/) (2026)
- [Do VLMs Perceive or Recall? Probing Visual Perception vs. Memory with Classic Visual Illusions](https://mlsanity.com/paper/2601.22150/) (2026)
- [Seeing Sarcasm Through Different Eyes: Analyzing Multimodal Sarcasm Perception in Large Vision-Language Models](https://mlsanity.com/paper/2503.12149/) (2025)
- [Multimodal Protein Language Models for Enzyme Kinetic Parameters: From Substrate Recognition to Conformational Adaptation](https://mlsanity.com/paper/2603.12845/) (2026)
- [MER-Bench: A Comprehensive Benchmark for Multimodal Meme Reappraisal](https://mlsanity.com/paper/2603.15020/) (2026)

## Abstract (arXiv)

While Vision-Language Models (VLMs) have achieved state-of-the-art performance in general visual tasks, their perceptual robustness remains remarkably brittle when confronted with optical illusions. These failures are often attributed to shortcut heuristics, where models prioritize linguistic priors and memorized prototypes over direct visual evidence. In this work, we propose Structured Qualitative Inference (SQI), a training-free, data-centric framework designed to fortify visual grounding in frozen VLMs. SQI addresses perceptual anomalies through three systematic modules: (1) Axiomatic Constraint Injection, which suppresses erroneous metric estimations and quantitative hallucinations; (2) Hierarchical Scene Decomposition, which decouples target visual manifolds from complex background distractors; and (3) Counterfactual Self-Verification, an adversarial reasoning step that mitigates confirmation bias. By orchestrating these qualitative constraints at inference time, SQI effectively aligns high-level linguistic reasoning with low-level visual perception. Our framework was evaluated on the DataCV 2026 Challenge (Task I: Classic Illusion Understanding), where it ranked 2nd place overall. Experimental results demonstrate that SQI not only significantly enhances accuracy across diverse illusion categories but also provides superior diagnostic interpretability without any model fine-tuning. Our success underscores the potential of structured qualitative grounding as a robust paradigm for developing next-generation, illusion-resistant vision-language systems.