Learning to Erase Private Knowledge from Multi-Documents for Retrieval-Augmented Large Language Models
Retrieval-Augmented Generation (RAG) is a promising technique for applying LLMs to proprietary domains. However, retrieved documents may contain sensitive knowledge, posing risks of privacy leakage in generative results. Thus, effectively erasing private information from retrieved documents is a key challenge for RAG.
研究重點
Retrieval-Augmented Generation (RAG) is a promising technique for applying LLMs to proprietary domains. However, retrieved documents may contain sensitive knowledge, posing risks of privacy leakage in generative results. Thus, effectively erasing private information from retrieved documents is a key challenge for RAG.
為什麼值得關注
這個議題涉及 Crew Pocket、Crew Deck 的實作方向。可先評估現有做法,再決定是否安排小型實驗。
可以進一步驗證什麼?
- 閱讀原文,確認它解決的問題、實驗方法及適用限制
- 檢查相關功能現有做法,找出可比較的差異
- 用小型 PoC 驗證成功率、品質、延遲和實際成本
參考資料
Learning to Erase Private Knowledge from Multi-Documents for Retrieval-Augmented Large Language Models ↗2026-11-03T00:00:00Z · 研究論文索引
延伸探索
相關研究
- Curriculum-aligned analysis of assessment feedback: a retrieval-augmented large language model approach for revealing fine-grained student error patterns in higher educat相同研究主題 · 2026-11-17
- MIRAGE: Misleading Retrieval-Augmented Generation via Black-box and Query-agnostic Poisoning Attacks相同研究主題 · 2026-11-14
- When Sources Disagree: Accuracy-Preserving Batch Verification and the Limits of Source-Age Screening in Retrieval-Augmented Generation相同研究主題 · 2026-11-12