# Knowledge Swapping via Learning and Unlearning

arXiv: https://arxiv.org/abs/2502.08075 · HTML: https://mlsanity.com/paper/2502.08075/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Machine unlearning, one of 12 directions in LLM safety and security.
- First posted on arXiv 12 Feb 2025.

## Placed in

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

## Built on by (most cited first, 3 of 3)

- [ReLearn: Unlearning via Learning for Large Language Models](https://mlsanity.com/paper/2502.11190/) (2025)
- [AffectAgent: Collaborative Multi-Agent Reasoning for Retrieval-Augmented Multimodal Emotion Recognition](https://mlsanity.com/paper/2604.12735/) (2026)
- [Data-Free Privacy-Preserving for LLMs via Model Inversion and Selective Unlearning](https://mlsanity.com/paper/2601.15595/) (2026)

## Abstract (arXiv)

We introduce Knowledge Swapping, a novel task designed to selectively regulate knowledge of a pretrained model by enabling the forgetting of user-specified information, retaining essential knowledge, and acquiring new knowledge simultaneously. By delving into the analysis of knock-on feature hierarchy, we find that incremental learning typically progresses from low-level representations to higher-level semantics, whereas forgetting tends to occur in the opposite direction-starting from high-level semantics and moving down to low-level features. Building upon this, we propose to benchmark the knowledge swapping task with the strategy of textitLearning Before Forgetting. Comprehensive experiments on various tasks like image classification, object detection, and semantic segmentation validate the effectiveness of the proposed strategy. The source code is available at hrefhttps://github.com/xingmingyu123456/KnowledgeSwappinghttps://github.com/xingmingyu123456/KnowledgeSwapping.