Scoutari

AI builder 的決策情報台。

瀏覽

  • 今日情報
  • Skill 榜單
  • AI 週報
  • 關於與編輯方針
  • RSS

主題

  • 模型發布
  • API 與價格
  • MCP 與 Skills
  • AI Coding
  • 中國模型
  • 開源模型
  • Agent
  • Infra / 成本
  • 值得試用
© 2026 Scoutari · scoutari.com摘要由 AI 輔助生成,並始終附上原文連結。
情報模型收藏週報設定
Tuesday, July 7, 2026Scoutari
Log inSign up
Sign up
ModelsSkill RadarSavedPersonalizeSubmit sourceLog in
IntelModelsSkill RadarWeeklySavedPersonalizeSubmit source
Back to timeline

Tue, July 706:23Model/APIEnterprise AI

Amazon Nova's Selective Forgetting: rDPO Reduces Over-Refusal

View original

Decision Brief

What changedAmazon Nova introduces rDPO-based selective forgetting for customizable content moderation, reducing over-refusal while maintaining model quality.
Why it mattersDevelopers using Amazon Nova can achieve more precise content filtering with rDPO, reducing false positives without sacrificing model performance.
Who should careTeams building on model APIs
Affected stackNo specific stack identified
Source confidenceHigh · Official release / blog / repo

Amazon Nova's Customizable Content Moderation Settings (CCMS) now include Reverse Direct Preference Optimization (rDPO), a new selective forgetting technique. rDPO enables the model to 'forget' specific content types while retaining normal processing for others. By reversing preference optimization, it reduces over-refusal—instances where content is incorrectly blocked—without compromising quality. For developers and enterprises, rDPO offers flexible content governance. Users can define custom moderation rules for scenarios like social media or e-commerce, precisely filtering unwanted content while minimizing false positives. AWS provides guidance on applying these techniques for similar results in user experiments.

Summary basis: official / RSS sourceCompiled from the source scope noted above; the original remains authoritative.

Sources

  • AWS:Machine Learning Blog

    Applied ML, infra, and deployment guidance useful for AI builders on AWS.

  • AWS:Machine Learning Blog

Related intel

  • China Z.ai Lab Releases GLM-5.2, the Strongest Open-Source Text LLM

    Z.ai Lab open-sourced GLM-5.2, a 753B parameter text-only LLM, on June 16.

  • GLM-5.2 passes vibe check, open-source models enter frontier

    GLM-5.2 has passed the collective vibe check, marking a milestone for open-source models.

  • OpenAI Releases GPT-5.6 Sol/Terra/Luna, Trusted Partners Only

    OpenAI launched tiered GPT-5.6 Sol/Terra/Luna models to OAI and ANT on the same day.

  • Gemini 3.5 Flash Gains Computer Use Ability

    Google DeepMind adds computer use to Gemini 3.5 Flash.