mlsanityData to 14 Oct 2026

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

arXiv 2511.13400 ↗First posted 17 Nov 2025cs.CVcited by 1

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

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.

Key facts. Cited by 1 paper 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.

Builds on

24 of 34 references.

Closest ancestors · 5

Same direction, newest first

  1. 2024From Pixels to Tokens: Revisiting Object Hallucinations in Large Vision-Language Models9 Oct
  2. 2024Multi-Object Hallucination in Vision-Language Models8 Jul
  3. 2024Hallucination of Multimodal Large Language Models: A Survey29 Apr
  4. 2023Detecting and Preventing Hallucinations in Large Vision Language Models11 Aug
  5. 2022Plausible May Not Be Faithful: Probing Object Hallucination in Vision-Language Pre-training14 Oct

Other references · 19

  1. 2025Qwen3 Technical Reportcited by 8,820
  2. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,234
  3. 2023Qwen Technical Reportcited by 3,344
  4. 2025Gemma 3 Technical Reportcited by 1,824
  5. 2025InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiencycited by 1,510
  6. 2023Aligning Large Multimodal Models with Factually Augmented RLHFcited by 712
  7. 2025Words or Vision: Do Vision-Language Models Have Blind Faith in Text?cited by 89
  8. 2024Insight Over Sight: Exploring the Vision-Knowledge Conflicts in Multimodal LLMscited by 38
  9. 2025Evaluating and Steering Modality Preferences in Multimodal Large Language Modelcited by 33
  10. 2024Unraveling Cross-Modality Knowledge Conflicts in Large Vision-Language Modelscited by 28
  11. 2025ColorBench: Can VLMs See and Understand the Colorful World? A Comprehensive Benchmark for Color Perception, Reasoning, and Robustnesscited by 28
  12. 2025Multimodal Inconsistency Reasoning (MMIR): A New Benchmark for Multimodal Reasoning Modelscited by 24
7 more
  1. 2025How Do Vision-Language Models Process Conflicting Information Across Modalities?cited by 23
  2. 2025When Modalities Conflict: How Unimodal Reasoning Uncertainty Governs Preference Dynamics in MLLMscited by 21
  3. 2025From Behavioral Performance to Internal Competence: Interpreting Vision-Language Models with VLM-Lenscited by 9
  4. 2025Diagnosing Vision Language Models' Perception by Leveraging Human Methods for Color Vision Deficienciescited by 2
  5. 2025ColorBlindnessEval: Can Vision-Language Models Pass Color Blindness Tests?cited by 2
  6. 2025Color Names in Vision-Language Modelscited by 2
  7. 2025Assessing Color Vision Test in Large Vision-language Modelscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Mechanisms of Prompt-Induced Hallucination in Vision-Language Modelscited by 5

Similar, not cited

Close in wording, no citation either way

  1. 2026LLM-as-Judge Framework for Evaluating Tone-Induced Hallucination in Vision-Language Models
  2. 2024Pensieve: Retrospect-then-Compare Mitigates Visual Hallucination
  3. 2024Visual Hallucination: Definition, Quantification, and Prescriptive Remediations
  4. 2026FREAK: A Fine-grained Hallucination Evaluation Benchmark for Advanced MLLMs
  5. 2026Reducing Object Hallucination in LVLMs via Emphasizing Image-negative Tokens
  6. 2025Hallucination as an Upper Bound: A New Perspective on Text-to-Image Evaluation
  7. 2025Two Causes, Not One: Rethinking Omission and Fabrication Hallucinations in MLLMs
  8. 2026Tone Matters: The Impact of Linguistic Tone on Hallucination in VLMs