# Learning to Detect Cross-Modal Negation: An Analysis of Latent Representations and an Attention-Based Solution

arXiv: https://arxiv.org/abs/2607.17712 · HTML: https://mlsanity.com/paper/2607.17712/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 33 references that are in the map.
- First posted on arXiv 20 Jul 2026.

## Builds on (most cited first, 13 of 13)

- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [The "something something" video database for learning and evaluating visual common sense](https://mlsanity.com/paper/1706.04261/) (2017)
- [Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture](https://mlsanity.com/paper/2301.08243/) (2023)
- [V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning](https://mlsanity.com/paper/2506.09985/) (2025)
- [FLAVA: A Foundational Language And Vision Alignment Model](https://mlsanity.com/paper/2112.04482/) (2021)
- [X-Pool: Cross-Modal Language-Video Attention for Text-Video Retrieval](https://mlsanity.com/paper/2203.15086/) (2022)
- [NegBio: a high-performance tool for negation and uncertainty detection in radiology reports](https://mlsanity.com/paper/1712.05898/) (2017)
- [Vision-Language Models Do Not Understand Negation](https://mlsanity.com/paper/2501.09425/) (2025)
- [NegBERT: A Transfer Learning Approach for Negation Detection and Scope Resolution](https://mlsanity.com/paper/1911.04211/) (2019)
- [Improving negation detection with negation-focused pre-training](https://mlsanity.com/paper/2205.04012/) (2022)
- [Thunder-NUBench: A Benchmark for LLMs' Sentence-Level Negation Understanding](https://mlsanity.com/paper/2506.14397/) (2025)
- [LINKED: Eliciting, Filtering and Integrating Knowledge in Large Language Model for Commonsense Reasoning](https://mlsanity.com/paper/2410.09541/) (2024)
- [Extending a Parliamentary Corpus with MPs' Tweets: Automatic Annotation and Evaluation Using MultiParTweet](https://mlsanity.com/paper/2512.11567/) (2025)

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

- [Negation Beyond the Verbal Channel: Temporal Multimodal Correlates in Dialogue](https://mlsanity.com/paper/2609.16396/) (2026)

## Abstract (arXiv)

Detecting high-level semantic concepts like negation across modalities remains a challenge for current multimodal systems. We analyze this as a fundamental representation learning problem, providing the first evidence that negation does not form a linearly or non-linearly separable class in the latent spaces of standard vision-language models (VLMs). We demonstrate that pretrained embeddings primarily encode modality-specific features, lacking a generalizable negation signal. To overcome this, we propose a novel cross-modal attention architecture that explicitly models inter-modal dependencies, achieving performance gains of up to +7.03% F1 over unimodal baselines. Our analysis reveals a key asymmetry: while textual negation often appears independently, visual negation is semantically dependent on linguistic context, a finding validated through our statistical analysis of 3,222 political video-text pairs automatically annotated via textscQwen2.5-VL. By combining this analysis with self-supervised video representations (JEPA2), we advance the modeling of temporal negation. This work provides new methods and insights for learning robust, semantically-aligned representations in multimodal systems.