# Beyond Superficial Forgetting: Thorough Unlearning through Knowledge Density Estimation and Block Re-insertion

arXiv: https://arxiv.org/abs/2511.11667 · HTML: https://mlsanity.com/paper/2511.11667/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Machine unlearning, one of 12 directions in LLM safety and security.
- Builds on 17 of its 30 references that are in the map.
- First posted on arXiv 11 Nov 2025.

## Placed in

- LLM safety and security / [Machine unlearning](https://mlsanity.com/safety/machine-unlearning/)

## Builds on (most cited first, 17 of 17)

- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [Transformer Feed-Forward Layers Are Key-Value Memories](https://mlsanity.com/paper/2012.14913/) (2020)
- [The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale](https://mlsanity.com/paper/2406.17557/) (2024)
- [Steering Llama 2 via Contrastive Activation Addition](https://mlsanity.com/paper/2312.06681/) (2023)
- [AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback](https://mlsanity.com/paper/2305.14387/) (2023)
- [Prompt Injection attack against LLM-integrated Applications](https://mlsanity.com/paper/2306.05499/) (2023)
- [TOFU: A Task of Fictitious Unlearning for LLMs](https://mlsanity.com/paper/2401.06121/) (2024)
- [Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning](https://mlsanity.com/paper/2404.05868/) (2024)
- [Knowledge Unlearning for Mitigating Privacy Risks in Language Models](https://mlsanity.com/paper/2210.01504/) (2022)
- [Are Large Pre-Trained Language Models Leaking Your Personal Information?](https://mlsanity.com/paper/2205.12628/) (2022)
- [Reinforcement Learning for LLM Post-Training: A Survey](https://mlsanity.com/paper/2407.16216/) (2024)
- [Soft Prompt Threats: Attacking Safety Alignment and Unlearning in Open-Source LLMs through the Embedding Space](https://mlsanity.com/paper/2402.09063/) (2024)
- [Copyright Protection in Generative AI: A Technical Perspective](https://mlsanity.com/paper/2402.02333/) (2024)
- [Simulating Financial Market via Large Language Model based Agents](https://mlsanity.com/paper/2406.19966/) (2024)
- [Learning to Refuse: Towards Mitigating Privacy Risks in LLMs](https://mlsanity.com/paper/2407.10058/) (2024)
- [Protecting Privacy Through Approximating Optimal Parameters for Sequence Unlearning in Language Models](https://mlsanity.com/paper/2406.14091/) (2024)

## Abstract (arXiv)

Machine unlearning, which selectively removes harmful knowledge from a pre-trained model without retraining from scratch, is crucial for addressing privacy, regulatory compliance, and ethical concerns in Large Language Models (LLMs). However, existing unlearning methods often struggle to thoroughly remove harmful knowledge, leaving residual harmful knowledge that can be easily recovered. To address these limitations, we propose Knowledge Density-Guided Unlearning via Blocks Reinsertion (KUnBR), a novel approach that first identifies layers with rich harmful knowledge and then thoroughly eliminates the harmful knowledge via re-insertion strategy. Our method introduces knowledge density estimation to quantify and locate layers containing the most harmful knowledge, enabling precise unlearning. Additionally, we design a layer re-insertion strategy that extracts and re-inserts harmful knowledge-rich layers into the original LLM, bypassing gradient obstruction caused by cover layers and ensuring effective gradient propagation during unlearning. Extensive experiments conducted on several unlearning and general capability benchmarks demonstrate that KUnBR achieves state-of-the-art forgetting performance while maintaining model utility.