# SUGARCREPE++ Dataset: Vision-Language Model Sensitivity to Semantic and Lexical Alterations

arXiv: https://arxiv.org/abs/2406.11171 · HTML: https://mlsanity.com/paper/2406.11171/

## Key facts

- Cited by 42 papers in the map (data through 14 Oct 2026).
- Placed in VLM benchmarks and visual reasoning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 72 of its 119 references that are in the map.
- First posted on arXiv 17 Jun 2024.

## Placed in

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

## Builds on (most cited first, 30 of 72)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering](https://mlsanity.com/paper/1612.00837/) (2016)
- [VQA: Visual Question Answering](https://mlsanity.com/paper/1505.00468/) (2015)
- [Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models](https://mlsanity.com/paper/2206.04615/) (2022)
- [Align before Fuse: Vision and Language Representation Learning with Momentum Distillation](https://mlsanity.com/paper/2107.07651/) (2021)
- [MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers](https://mlsanity.com/paper/2002.10957/) (2020)
- [Calibrate Before Use: Improving Few-Shot Performance of Language Models](https://mlsanity.com/paper/2102.09690/) (2021)
- [Text Embeddings by Weakly-Supervised Contrastive Pre-training](https://mlsanity.com/paper/2212.03533/) (2022)
- [ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision](https://mlsanity.com/paper/2102.03334/) (2021)
- [COCO-Stuff: Thing and Stuff Classes in Context](https://mlsanity.com/paper/1612.03716/) (2016)
- [Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting](https://mlsanity.com/paper/2310.11324/) (2023)
- [BERTopic: Neural topic modeling with a class-based TF-IDF procedure](https://mlsanity.com/paper/2203.05794/) (2022)
- [ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate](https://mlsanity.com/paper/2308.07201/) (2023)
- [FLAVA: A Foundational Language And Vision Alignment Model](https://mlsanity.com/paper/2112.04482/) (2021)
- [DataComp: In search of the next generation of multimodal datasets](https://mlsanity.com/paper/2304.14108/) (2023)

## Built on by (most cited first, 30 of 42)

- [VL-JEPA: Joint Embedding Predictive Architecture for Vision-language](https://mlsanity.com/paper/2512.10942/) (2025)
- [Reasoning on a Spectrum: Aligning LLMs to System 1 and System 2 Thinking](https://mlsanity.com/paper/2502.12470/) (2025)
- [VladVA: Discriminative Fine-tuning of LVLMs](https://mlsanity.com/paper/2412.04378/) (2024)
- [CLIP Under the Microscope: A Fine-Grained Analysis of Multi-Object Representation](https://mlsanity.com/paper/2502.19842/) (2025)
- [Enhancing Vision-Language Compositional Understanding with Multimodal Synthetic Data](https://mlsanity.com/paper/2503.01167/) (2025)
- [Mixed Signals: Decoding VLMs' Reasoning and Underlying Bias in Vision-Language Conflict](https://mlsanity.com/paper/2504.08974/) (2025)
- [Diffusion Classifiers Understand Compositionality, but Conditions Apply](https://mlsanity.com/paper/2505.17955/) (2025)
- [Advancing Compositional Awareness in CLIP with Efficient Fine-Tuning](https://mlsanity.com/paper/2505.24424/) (2025)
- [A Good CREPE needs more than just Sugar: Investigating Biases in Compositional Vision-Language Benchmarks](https://mlsanity.com/paper/2506.08227/) (2025)
- [From Generator to Embedder: Harnessing Innate Abilities of Multimodal LLMs via Building Zero-Shot Discriminative Embedding Model](https://mlsanity.com/paper/2508.00955/) (2025)
- [Evaluating Compositional Generalisation in VLMs and Diffusion Models](https://mlsanity.com/paper/2508.20783/) (2025)
- [Resolving Lexical Bias in Model Editing](https://mlsanity.com/paper/2408.10411/) (2024)
- [Common Data Properties Limit Object-Attribute Binding in CLIP](https://mlsanity.com/paper/2507.07985/) (2025)
- [Seeing Syntax: Uncovering Syntactic Learning Limitations in Vision-Language Models](https://mlsanity.com/paper/2412.08111/) (2024)
- [Sensitivity of Generative VLMs to Semantically and Lexically Altered Prompts](https://mlsanity.com/paper/2410.13030/) (2024)
- [SPECS: Specificity-Enhanced CLIP-Score for Long Image Caption Evaluation](https://mlsanity.com/paper/2509.03897/) (2025)
- [Enhancing Compositional Reasoning in CLIP via Reconstruction and Alignment of Text Descriptions](https://mlsanity.com/paper/2510.16540/) (2025)
- [Reward Prediction with Factorized World States](https://mlsanity.com/paper/2603.09400/) (2026)
- [RemoteShield: Enable Robust Multimodal Large Language Models for Earth Observation](https://mlsanity.com/paper/2604.17243/) (2026)
- [Understanding Space Is Rocket Science -- Only Top Reasoning Models Can Solve Spatial Understanding Tasks](https://mlsanity.com/paper/2509.02175/) (2025)
- [PowerCLIP: Powerset Alignment for Contrastive Pre-Training](https://mlsanity.com/paper/2511.23170/) (2025)
- [PolyGen: Fully Synthetic Vision-Language Training via Multi-Generator Ensembles](https://mlsanity.com/paper/2602.01370/) (2026)
- [On the Persistent Effects of Lexicality in Large Language Models](https://mlsanity.com/paper/2606.02750/) (2026)
- [On Debiasing Text Embeddings Through Context Injection](https://mlsanity.com/paper/2410.12874/) (2024)
- [A New Method to Capturing Compositional Knowledge in Linguistic Space](https://mlsanity.com/paper/2412.15632/) (2024)
- [Beyond General Prompts: Automated Prompt Refinement using Contrastive Class Alignment Scores for Disambiguating Objects in Vision-Language Models](https://mlsanity.com/paper/2505.09139/) (2025)
- [Long Story Short: Disentangling Compositionality and Long-Caption Understanding in Contrastive VLMs](https://mlsanity.com/paper/2509.19207/) (2025)
- [What's in Common? Multimodal Models Hallucinate When Reasoning Across Scenes](https://mlsanity.com/paper/2511.03768/) (2025)
- [Contrastive vision-language learning with paraphrasing and negation](https://mlsanity.com/paper/2511.16527/) (2025)
- [Auto-Comp: An Automated Pipeline for Scalable Compositional Probing of Contrastive Vision-Language Models](https://mlsanity.com/paper/2602.02043/) (2026)

## Abstract (arXiv)

Despite their remarkable successes, state-of-the-art large language models (LLMs), including vision-and-language models (VLMs) and unimodal language models (ULMs), fail to understand precise semantics. For example, semantically equivalent sentences expressed using different lexical compositions elicit diverging representations. The degree of this divergence and its impact on encoded semantics is not very well understood. In this paper, we introduce the SUGARCREPE++ dataset to analyze the sensitivity of VLMs and ULMs to lexical and semantic alterations. Each sample in SUGARCREPE++ dataset consists of an image and a corresponding triplet of captions: a pair of semantically equivalent but lexically different positive captions and one hard negative caption. This poses a 3-way semantic (in)equivalence problem to the language models. We comprehensively evaluate VLMs and ULMs that differ in architecture, pre-training objectives and datasets to benchmark the performance of SUGARCREPE++ dataset. Experimental results highlight the difficulties of VLMs in distinguishing between lexical and semantic variations, particularly in object attributes and spatial relations. Although VLMs with larger pre-training datasets, model sizes, and multiple pre-training objectives achieve better performance on SUGARCREPE++, there is a significant opportunity for improvement. We show that all the models which achieve better performance on compositionality datasets need not perform equally well on SUGARCREPE++, signifying that compositionality alone may not be sufficient for understanding semantic and lexical alterations. Given the importance of the property that the SUGARCREPE++ dataset targets, it serves as a new challenge to the vision-and-language community.