@article{understandingandmitigatingtoxicityin, title = {Understanding and Mitigating Toxicity in Image-Text Pretraining Datasets: A Case Study on LLaVA}, author = {Karthik Reddy Kanjula and Surya Guthikonda and Nahid Alam and Shayekh Bin Islam}, year = {2025}, eprint = {2505.06356}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.06356v1}, }