# Do not think about pink elephant!

arXiv: https://arxiv.org/abs/2404.15154 · HTML: https://mlsanity.com/paper/2404.15154/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 17 references that are in the map.
- First posted on arXiv 22 Apr 2024.

## Builds on (most cited first, 9 of 9)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere](https://mlsanity.com/paper/2005.10242/) (2020)
- [Scaling Autoregressive Models for Content-Rich Text-to-Image Generation](https://mlsanity.com/paper/2206.10789/) (2022)
- [GLM-130B: An Open Bilingual Pre-trained Model](https://mlsanity.com/paper/2210.02414/) (2022)
- [Trustworthy AI: From Principles to Practices](https://mlsanity.com/paper/2110.01167/) (2021)
- [Safety and Fairness for Content Moderation in Generative Models](https://mlsanity.com/paper/2306.06135/) (2023)

## Built on by (most cited first, 4 of 4)

- [Controlling Language and Diffusion Models by Transporting Activations](https://mlsanity.com/paper/2410.23054/) (2024)
- [Feedback That Backfires: Why Small Language Model Agents Repeat the Call They Just Watched Fail](https://mlsanity.com/paper/2608.23651/) (2026)
- [Don't Think of the White Bear: Ironic Negation in Transformer Models Under Cognitive Load](https://mlsanity.com/paper/2511.12381/) (2025)
- [Discriminative Score Function: Turning Pretrained Models into Functional Generative Priors](https://mlsanity.com/paper/2610.19743/) (2026)

## Abstract (arXiv)

Large Models (LMs) have heightened expectations for the potential of general AI as they are akin to human intelligence. This paper shows that recent large models such as Stable Diffusion and DALL-E3 also share the vulnerability of human intelligence, namely the "white bear phenomenon". We investigate the causes of the white bear phenomenon by analyzing their representation space. Based on this analysis, we propose a simple prompt-based attack method, which generates figures prohibited by the LM provider's policy. To counter these attacks, we introduce prompt-based defense strategies inspired by cognitive therapy techniques, successfully mitigating attacks by up to 48.22%.