Real Images, Worse Judgments: Evaluating Vision-Language Models on Concreteness and Imagery

• URL: http://arxiv.org/abs/2605.27315v1
• Date: Tue, 26 May 2026 17:24:59 GMT
• Title: Real Images, Worse Judgments: Evaluating Vision-Language Models on Concreteness and Imagery
• Abstract summary: We study whether vision-language models can distinguish useful visual evidence from incidental image context in lexical judgments.<n>We find that real-image contexts do not yield consistent gains and often hurt alignment with human ratings.<n>Our findings suggest that current instruction-tuned VLMs need better calibration of when visual context should inform lexical judgments.
• Score: 21.95600321802019
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Visual inputs are often assumed to improve language understanding in multimodal models. We examine this assumption by asking whether vision-language models (VLMs) can distinguish useful visual evidence from incidental image context in lexical judgments. We use human concreteness and imagery ratings because they span words with varying expected visual relevance, from abstract and low-imagery words to concrete and high-imagery words. We find that real-image contexts do not yield consistent gains and often hurt alignment with human ratings, most sharply when visual evidence is least relevant. Through probing and canonical correlation analysis, complemented by an attribution case study, we find that real-image contexts are associated with representational shifts and greater sensitivity to spurious visual cues, coinciding with weaker recoverability of the targeted lexical properties. We further show that instructing models to focus solely on textual content at inference time can reduce this degradation, with the clearest gains on these vulnerable subsets. Our findings suggest that current instruction-tuned VLMs need better calibration of when visual context should inform lexical judgments.

Related papers

• More Than Meets the Eye: Measuring the Semiotic Gap in Vision-Language Models via Semantic Anchorage [3.968258676030377]
  We study whether high visual fidelity interferes with idiomatic compositionality under visual abstraction.<n>We introduce DIVA, a benchmark that replaces high-fidelity visual detail with schematic iconicity by generating paired, sense-anchored visualizations for literal and idiomatic readings.<n>Our findings suggest that improving compositional understanding requires iconographic abstraction of visual input and anchoring interpretation and generation in intended meaning.
  arXiv  Detail & Related papers  (2026-04-19T10:00:41Z)
• Chatting with Images for Introspective Visual Thinking [50.7747647794877]
  ''Chatting with images'' is a new framework that reframes visual manipulation as language-guided feature modulation.<n>Under the guidance of expressive language prompts, the model dynamically performs joint re-encoding over multiple image regions.<n>ViLaVT achieves strong and consistent improvements on complex multi-image and video-based spatial reasoning tasks.
  arXiv  Detail & Related papers  (2026-02-11T17:42:37Z)
• Evaluating the encoding competence of visual language models using uncommon actions [5.816389980109022]
  UAIT is a new evaluation benchmark designed to test the semantic understanding ability of visual language models (VLMs) in uncommon-sense action scenes.<n>We synthesize high-quality uncommon-sense image-text samples using large language models, few-shot prompt engineering, and text-to-image generation.<n>We evaluate multiple state-of-the-art visual language models and compare them with models based on contrastive learning.
  arXiv  Detail & Related papers  (2026-01-12T17:15:45Z)
• ViCrit: A Verifiable Reinforcement Learning Proxy Task for Visual Perception in VLMs [98.27348724529257]
  We introduce ViCrit (Visual Caption Hallucination Critic), an RL proxy task that trains VLMs to localize a subtle, synthetic visual hallucination injected into paragraphs of human-written image captions.<n>Models trained with the ViCrit Task exhibit substantial gains across a variety of vision-language models benchmarks.
  arXiv  Detail & Related papers  (2025-06-11T19:16:54Z)
• Retrieval-Based Interleaved Visual Chain-of-Thought in Real-World Driving Scenarios [69.00444996464662]
  We propose RIV-CoT, a Retrieval-Based Interleaved Visual Chain-of-Thought method that enables vision-language models to reason using visual crops corresponding to relevant entities.<n>Our experiments demonstrate that RIV-CoT improves answer accuracy by 3.1% and reasoning accuracy by 4.6% over vanilla CoT prompting.
  arXiv  Detail & Related papers  (2025-01-08T18:31:16Z)
• Vision Language Model-based Caption Evaluation Method Leveraging Visual Context Extraction [27.00018283430169]
  This paper presents VisCE$2$, a vision language model-based caption evaluation method. Our method focuses on visual context, which refers to the detailed content of images, including objects, attributes, and relationships.
  arXiv  Detail & Related papers  (2024-02-28T01:29:36Z)
• Perceptual Grouping in Contrastive Vision-Language Models [59.1542019031645]
  We show how vision-language models are able to understand where objects reside within an image and group together visually related parts of the imagery. We propose a minimal set of modifications that results in models that uniquely learn both semantic and spatial information.
  arXiv  Detail & Related papers  (2022-10-18T17:01:35Z)
• Consensus Graph Representation Learning for Better Grounded Image Captioning [48.208119537050166]
  We propose the Consensus Rraph Representation Learning framework (CGRL) for grounded image captioning. We validate the effectiveness of our model, with a significant decline in object hallucination (-9% CHAIRi) on the Flickr30k Entities dataset.
  arXiv  Detail & Related papers  (2021-12-02T04:17:01Z)
• Improving Image Captioning with Better Use of Captions [65.39641077768488]
  We present a novel image captioning architecture to better explore semantics available in captions and leverage that to enhance both image representation and caption generation. Our models first construct caption-guided visual relationship graphs that introduce beneficial inductive bias using weakly supervised multi-instance learning. During generation, the model further incorporates visual relationships using multi-task learning for jointly predicting word and object/predicate tag sequences.
  arXiv  Detail & Related papers  (2020-06-21T14:10:47Z)
• Probing Contextual Language Models for Common Ground with Visual Representations [76.05769268286038]
  We design a probing model that evaluates how effective are text-only representations in distinguishing between matching and non-matching visual representations. Our findings show that language representations alone provide a strong signal for retrieving image patches from the correct object categories. Visually grounded language models slightly outperform text-only language models in instance retrieval, but greatly under-perform humans.
  arXiv  Detail & Related papers  (2020-05-01T21:28:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.