# DILLEMA: Diffusion and Large Language Models for Multi-Modal Augmentation

arXiv: https://arxiv.org/abs/2502.04378 · HTML: https://mlsanity.com/paper/2502.04378/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models.
- Builds on 16 of its 22 references that are in the map.
- First posted on arXiv 5 Feb 2025.

## Placed in

- Diffusion models / [Image generation, text-to-image and editing](https://mlsanity.com/diffusion/image-generation-text-to-image-and-editing/)

## Builds on (most cited first, 16 of 16)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [DeepXplore: Automated Whitebox Testing of Deep Learning Systems](https://mlsanity.com/paper/1705.06640/) (2017)
- [DeepTest: Automated Testing of Deep-Neural-Network-driven Autonomous Cars](https://mlsanity.com/paper/1708.08559/) (2017)
- [Machine Learning Testing: Survey, Landscapes and Horizons](https://mlsanity.com/paper/1906.10742/) (2019)
- [SHIFT: A Synthetic Driving Dataset for Continuous Multi-Task Domain Adaptation](https://mlsanity.com/paper/2206.08367/) (2022)
- [Diversify Your Vision Datasets with Automatic Diffusion-Based Augmentation](https://mlsanity.com/paper/2305.16289/) (2023)
- [DeepBillboard: Systematic Physical-World Testing of Autonomous Driving Systems](https://mlsanity.com/paper/1812.10812/) (2018)
- [Dataset Interfaces: Diagnosing Model Failures Using Controllable Counterfactual Generation](https://mlsanity.com/paper/2302.07865/) (2023)
- [Advances in Diffusion Models for Image Data Augmentation: A Review of Methods, Models, Evaluation Metrics and Future Research Directions](https://mlsanity.com/paper/2407.04103/) (2024)
- [Efficient Domain Augmentation for Autonomous Driving Testing Using Diffusion Models](https://mlsanity.com/paper/2409.13661/) (2024)

## Built on by (most cited first, 3 of 3)

- [A Multi-Modality Evaluation of the Reality Gap in Autonomous Driving Systems](https://mlsanity.com/paper/2509.22379/) (2025)
- [GAN-enhanced Simulation-driven DNN Testing in Absence of Ground Truth](https://mlsanity.com/paper/2503.15953/) (2025)
- [SeFaR: Semantic Feature-aware Robustness Testing of Deep Neural Networks](https://mlsanity.com/paper/2608.10289/) (2026)

## Abstract (arXiv)

Ensuring the robustness of deep learning models requires comprehensive and diverse testing. Existing approaches, often based on simple data augmentation techniques or generative adversarial networks, are limited in producing realistic and varied test cases. To address these limitations, we present a novel framework for testing vision neural networks that leverages Large Language Models and control-conditioned Diffusion Models to generate synthetic, high-fidelity test cases. Our approach begins by translating images into detailed textual descriptions using a captioning model, allowing the language model to identify modifiable aspects of the image and generate counterfactual descriptions. These descriptions are then used to produce new test images through a text-to-image diffusion process that preserves spatial consistency and maintains the critical elements of the scene. We demonstrate the effectiveness of our method using two datasets: ImageNet1K for image classification and SHIFT for semantic segmentation in autonomous driving. The results show that our approach can generate significant test cases that reveal weaknesses and improve the robustness of the model through targeted retraining. We conducted a human assessment using Mechanical Turk to validate the generated images. The responses from the participants confirmed, with high agreement among the voters, that our approach produces valid and realistic images.