Get the latest tech news
DeepSeek's Hidden Bias: How We Cut It by 76% Without Performance Loss
Showcasing Hirundo’s bias unlearning capabilities on DeepSeek-R1-Distill-Llama-8B, reducing its biases up to 76% compared to original performance.
Our results demonstrate that, even with new and emerging models, we can significantly reduce bias—up to 76% reduction as compared to its original state—without compromising performance, offering a robust proof of concept for safer AI deployment. This experiment not only showcases how Hirundo’s unlearning methods can enhance emerging models but also underscores our commitment to enabling safer, more reliable AI deployments—even for cutting-edge systems like those developed by DeepSeek. In this use case, we utilized a proprietary method - soon live on our platform - that can remove bias from any open-source LLM, typically within an hour on moderate computing resources and for commonly used model sizes.
Or read this on Hacker News
