# Learn "No" to Say "Yes" Better: Improving Vision-Language Models via Negations

arXiv: https://arxiv.org/abs/2403.20312 · HTML: https://mlsanity.com/paper/2403.20312/

## Key facts

- Cited by 46 papers in the map (data through 14 Oct 2026).
- Placed in Prompt learning and adaptation of CLIP, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 39 of its 61 references that are in the map.
- First posted on arXiv 29 Mar 2024.

## Placed in

- Multimodal LLMs / vision-language models / [Prompt learning and adaptation of CLIP](https://mlsanity.com/mllm/prompt-learning-and-adaptation-of-clip/)

## Builds on (most cited first, 30 of 39)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks](https://mlsanity.com/paper/1908.02265/) (2019)
- [LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs](https://mlsanity.com/paper/2111.02114/) (2021)
- [Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?](https://mlsanity.com/paper/2202.12837/) (2022)
- [VisualBERT: A Simple and Performant Baseline for Vision and Language](https://mlsanity.com/paper/1908.03557/) (2019)
- [Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts](https://mlsanity.com/paper/2102.08981/) (2021)
- [Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks](https://mlsanity.com/paper/2004.06165/) (2020)
- [PaLM 2 Technical Report](https://mlsanity.com/paper/2305.10403/) (2023)
- [An Explanation of In-context Learning as Implicit Bayesian Inference](https://mlsanity.com/paper/2111.02080/) (2021)
- [FLAVA: A Foundational Language And Vision Alignment Model](https://mlsanity.com/paper/2112.04482/) (2021)
- [When and why vision-language models behave like bags-of-words, and what to do about it?](https://mlsanity.com/paper/2210.01936/) (2022)
- [LiT: Zero-Shot Transfer with Locked-image text Tuning](https://mlsanity.com/paper/2111.07991/) (2021)
- [SLIP: Self-supervision meets Language-Image Pre-training](https://mlsanity.com/paper/2112.12750/) (2021)
- [AudioCLIP: Extending CLIP to Image, Text and Audio](https://mlsanity.com/paper/2106.13043/) (2021)
- [Simple Open-Vocabulary Object Detection with Vision Transformers](https://mlsanity.com/paper/2205.06230/) (2022)
- [Negated and Misprimed Probes for Pretrained Language Models: Birds Can Talk, But Cannot Fly](https://mlsanity.com/paper/1911.03343/) (2019)
- [SugarCrepe: Fixing Hackable Benchmarks for Vision-Language Compositionality](https://mlsanity.com/paper/2306.14610/) (2023)
- [Improving CLIP Training with Language Rewrites](https://mlsanity.com/paper/2305.20088/) (2023)
- [StableVideo: Text-driven Consistency-aware Diffusion Video Editing](https://mlsanity.com/paper/2308.09592/) (2023)
- [CREPE: Can Vision-Language Foundation Models Reason Compositionally?](https://mlsanity.com/paper/2212.07796/) (2022)
- [RedCaps: web-curated image-text data created by the people, for the people](https://mlsanity.com/paper/2111.11431/) (2021)

## Built on by (most cited first, 30 of 46)

- [LamRA: Large Multimodal Model as Your Advanced Retrieval Assistant](https://mlsanity.com/paper/2412.01720/) (2024)
- [Vision-Language Models Do Not Understand Negation](https://mlsanity.com/paper/2501.09425/) (2025)
- [TripletCLIP: Improving Compositional Reasoning of CLIP via Synthetic Vision-Language Negatives](https://mlsanity.com/paper/2411.02545/) (2024)
- [INQUIRE: A Natural World Text-to-Image Retrieval Benchmark](https://mlsanity.com/paper/2411.02537/) (2024)
- [Dynamic Negative Guidance of Diffusion Models](https://mlsanity.com/paper/2410.14398/) (2024)
- [Know "No" Better: A Data-Driven Approach for Enhancing Negation Awareness in CLIP](https://mlsanity.com/paper/2501.10913/) (2025)
- [Is CLIP ideal? No. Can we fix it? Yes!](https://mlsanity.com/paper/2503.08723/) (2025)
- [Preserving Multi-Modal Capabilities of Pre-trained VLMs for Improving Vision-Linguistic Compositionality](https://mlsanity.com/paper/2410.05210/) (2024)
- [NegVQA: Can Vision Language Models Understand Negation?](https://mlsanity.com/paper/2505.22946/) (2025)
- [Enhancing Vision-Language Compositional Understanding with Multimodal Synthetic Data](https://mlsanity.com/paper/2503.01167/) (2025)
- [Bringing CLIP to the Clinic: Dynamic Soft Labels and Negation-Aware Learning for Medical Analysis](https://mlsanity.com/paper/2505.22079/) (2025)
- [U-MARVEL: Unveiling Key Factors for Universal Multimodal Retrieval via Embedding Learning with MLLMs](https://mlsanity.com/paper/2507.14902/) (2025)
- [Negation: A Pink Elephant in the Large Language Models' Room?](https://mlsanity.com/paper/2503.22395/) (2025)
- [TNG-CLIP:Training-Time Negation Data Generation for Negation Awareness of CLIP](https://mlsanity.com/paper/2505.18434/) (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)
- [Negation-Aware Test-Time Adaptation for Vision-Language Models](https://mlsanity.com/paper/2507.19064/) (2025)
- [VSF: Simple, Efficient, and Effective Negative Guidance in Few-Step Image Generation Models By Value Sign Flip](https://mlsanity.com/paper/2508.10931/) (2025)
- [NeIn: Telling What You Don't Want](https://mlsanity.com/paper/2409.06481/) (2024)
- [Benchmarking Gaslighting Negation Attacks Against Multimodal Large Language Models](https://mlsanity.com/paper/2501.19017/) (2025)
- [Trade-offs in Image Generation: How Do Different Dimensions Interact?](https://mlsanity.com/paper/2507.22100/) (2025)
- [On the Brittleness of CLIP Text Encoders](https://mlsanity.com/paper/2511.04247/) (2025)
- [NEGATE: Constrained Semantic Guidance for Linguistic Negation in Text-to-Video Diffusion](https://mlsanity.com/paper/2603.06533/) (2026)
- [Evaluating and Enhancing Negation Comprehension in Remote Sensing MLLMs](https://mlsanity.com/paper/2606.20177/) (2026)
- [From No to Know: Taxonomy, Challenges, and Opportunities for Negation Understanding in Multimodal Foundation Models](https://mlsanity.com/paper/2502.09645/) (2025)
- [RB-FT: Rationale-Bootstrapped Fine-Tuning for Video Classification](https://mlsanity.com/paper/2511.15923/) (2025)
- [Towards Effective Negation Modeling in Joint Audio-Text Models for Music](https://mlsanity.com/paper/2601.13931/) (2026)
- [Omni-NegCLIP: Enhancing CLIP with Front-Layer Contrastive Fine-Tuning for Comprehensive Negation Understanding](https://mlsanity.com/paper/2603.29258/) (2026)
- [Spatiotemporal Sycophancy: Negation-Based Gaslighting in Video Large Language Models](https://mlsanity.com/paper/2604.17873/) (2026)
- [DCR: Counterfactual Attractor Guidance for Rare Compositional Generation](https://mlsanity.com/paper/2605.06512/) (2026)

## Abstract (arXiv)

Existing vision-language models (VLMs) treat text descriptions as a unit, confusing individual concepts in a prompt and impairing visual semantic matching and reasoning. An important aspect of reasoning in logic and language is negations. This paper highlights the limitations of popular VLMs such as CLIP, at understanding the implications of negations, i.e., the effect of the word "not" in a given prompt. To enable evaluation of VLMs on fluent prompts with negations, we present CC-Neg, a dataset containing 228,246 images, true captions and their corresponding negated captions. Using CC-Neg along with modifications to the contrastive loss of CLIP, our proposed CoN-CLIP framework, has an improved understanding of negations. This training paradigm improves CoN-CLIP's ability to encode semantics reliably, resulting in 3.85% average gain in top-1 accuracy for zero-shot image classification across 8 datasets. Further, CoN-CLIP outperforms CLIP on challenging compositionality benchmarks such as SugarCREPE by 4.4%, showcasing emergent compositional understanding of objects, relations, and attributes in text. Overall, our work addresses a crucial limitation of VLMs by introducing a dataset and framework that strengthens semantic associations between images and text, demonstrating improved large-scale foundation models with significantly reduced computational cost, promoting efficiency and accessibility.