# Teaching Models to Forget: Selective Unlearning with Amazon Nova

> **Platform:** [SPIDITS AI](https://spidits.com/) — Real-Time AI News & Market Intelligence  
> **Published:** 2026-07-06T22:23:45.000Z  
> **Category:** PRODUCT_LAUNCH  
> **Impact Score:** 140/100  
> **Primary Source:** [AWS ML Blog](https://aws.amazon.com/blogs/machine-learning/teaching-models-to-forget-selective-unlearning-with-amazon-nova)  
> **Canonical Citation:** [https://spidits.com/timeline/teaching-models-to-forget-selective-unlearning-with-amazon-nova](https://spidits.com/timeline/teaching-models-to-forget-selective-unlearning-with-amazon-nova)

## Executive Summary
In this post, we introduce Reverse Direct Preference Optimization (rDPO), the novel unlearning technique behind Amazon Nova Customizable Content Moderation.

## Referenced Coverage & Sources
- **[AWS ML Blog](https://aws.amazon.com/blogs/machine-learning/teaching-models-to-forget-selective-unlearning-with-amazon-nova)**: Teaching models to forget: Selective unlearning with Amazon Nova — _In this post, we introduce Reverse Direct Preference Optimization (rDPO), the novel unlearning technique behind Amazon Nova Customizable Content Moderation..._

---
*Synthesized by SPIDITS AI Market Intelligence Desk. Track live AI news, model releases, and funding: [https://spidits.com](https://spidits.com)*