# What Color Is the Text? A Benchmark for Hallucination Induced by Image-Embedded Prompt

arXiv: https://arxiv.org/abs/2511.13400 · HTML: https://mlsanity.com/paper/2511.13400/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Hallucination mitigation in LVLMs, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 24 of its 34 references that are in the map.
- First posted on arXiv 17 Nov 2025.

## Placed in

- Multimodal LLMs / vision-language models / [Hallucination mitigation in LVLMs](https://mlsanity.com/mllm/hallucination-mitigation-in-lvlms/)

## Builds on (most cited first, 24 of 24)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Gemma 3 Technical Report](https://mlsanity.com/paper/2503.19786/) (2025)
- [InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency](https://mlsanity.com/paper/2508.18265/) (2025)
- [Aligning Large Multimodal Models with Factually Augmented RLHF](https://mlsanity.com/paper/2309.14525/) (2023)
- [Hallucination of Multimodal Large Language Models: A Survey](https://mlsanity.com/paper/2404.18930/) (2024)
- [Detecting and Preventing Hallucinations in Large Vision Language Models](https://mlsanity.com/paper/2308.06394/) (2023)
- [Words or Vision: Do Vision-Language Models Have Blind Faith in Text?](https://mlsanity.com/paper/2503.02199/) (2025)
- [Plausible May Not Be Faithful: Probing Object Hallucination in Vision-Language Pre-training](https://mlsanity.com/paper/2210.07688/) (2022)
- [Multi-Object Hallucination in Vision-Language Models](https://mlsanity.com/paper/2407.06192/) (2024)
- [Insight Over Sight: Exploring the Vision-Knowledge Conflicts in Multimodal LLMs](https://mlsanity.com/paper/2410.08145/) (2024)
- [Evaluating and Steering Modality Preferences in Multimodal Large Language Model](https://mlsanity.com/paper/2505.20977/) (2025)
- [Unraveling Cross-Modality Knowledge Conflicts in Large Vision-Language Models](https://mlsanity.com/paper/2410.03659/) (2024)
- [ColorBench: Can VLMs See and Understand the Colorful World? A Comprehensive Benchmark for Color Perception, Reasoning, and Robustness](https://mlsanity.com/paper/2504.10514/) (2025)
- [Multimodal Inconsistency Reasoning (MMIR): A New Benchmark for Multimodal Reasoning Models](https://mlsanity.com/paper/2502.16033/) (2025)
- [How Do Vision-Language Models Process Conflicting Information Across Modalities?](https://mlsanity.com/paper/2507.01790/) (2025)
- [When Modalities Conflict: How Unimodal Reasoning Uncertainty Governs Preference Dynamics in MLLMs](https://mlsanity.com/paper/2511.02243/) (2025)
- [From Behavioral Performance to Internal Competence: Interpreting Vision-Language Models with VLM-Lens](https://mlsanity.com/paper/2510.02292/) (2025)
- [From Pixels to Tokens: Revisiting Object Hallucinations in Large Vision-Language Models](https://mlsanity.com/paper/2410.06795/) (2024)
- [Diagnosing Vision Language Models' Perception by Leveraging Human Methods for Color Vision Deficiencies](https://mlsanity.com/paper/2505.17461/) (2025)
- [ColorBlindnessEval: Can Vision-Language Models Pass Color Blindness Tests?](https://mlsanity.com/paper/2509.19070/) (2025)
- [Color Names in Vision-Language Models](https://mlsanity.com/paper/2509.22524/) (2025)
- [Assessing Color Vision Test in Large Vision-language Models](https://mlsanity.com/paper/2507.11153/) (2025)

## Built on by (most cited first, 1 of 1)

- [Mechanisms of Prompt-Induced Hallucination in Vision-Language Models](https://mlsanity.com/paper/2601.05201/) (2026)

## Abstract (arXiv)

We introduce Embedded Stroop, a controlled diagnostic paradigm for measuring image-embedded prompt interference in Multimodal Large Language Models (MLLMs), where the query is rendered directly inside the visual input. Using the What-Color-Is-the-Text (WCIT) benchmark, which covers 59 fine-grained colors under Standard, Flipped, and Masked variants, we evaluate 16 proprietary and open-source models. To distinguish semantic capture from general color-naming failure, we decompose model responses into Accuracy, Stroop Hallucination Rate (SHR; answering the embedded word rather than the true text color), and Other Error Rate, and validate the effect with permutation tests, with 56 of 64 conditions remaining significant after FDR correction. Although exact color accuracy is low (6.3%) under the 59-color vocabulary, mapping predictions to 11 basic color families shows that models retain coarse color perception (38.4%) while still exhibiting a substantial SHR (21.6%). A conditional analysis restricted to colors correctly named in the Standard setting further confirms the effect, with pooled conditional SHR exceeding 50%. Masking or flipping the embedded text reduces Stroop hallucinations, suggesting that semantic legibility can dominate visual color perception in MLLMs.