Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2503.02701 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909524673167360 |
|---|---|
| author | Li, Shuaike Zhang, Kai Liu, Qi Chen, Enhong |
| author_facet | Li, Shuaike Zhang, Kai Liu, Qi Chen, Enhong |
| contents | Knowledge editing is a technique for efficiently and accurately updating the knowledge of large language models (LLMs) to alleviate obsolescence and correct errors. However, most existing methods overfit to specific models, causing edited knowledge to be discarded during each LLM update and requiring frequent re-editing, which is particularly burdensome in today's rapidly evolving open-source community. To address this issue, we propose the problem of cross-model knowledge editing and introduce MindBridge, a scalable solution inspired by the low coupling between modality processing and LLMs in multi-modal models. MindBridge introduces the novel concept of memory modality, which encodes edited knowledge as an independent modality. It first performs LLM-agnostic pre-training of the memory modality and then integrates it with various LLMs. Extensive experiments on multiple LLMs and popular knowledge editing datasets demonstrate that MindBridge achieves superior performance even in editing tens of thousands of knowledge entries and can flexibly adapt to different LLMs. Our code is available at https://github.com/CrashBugger/MindBridge. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_02701 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MindBridge: Scalable and Cross-Model Knowledge Editing via Memory-Augmented Modality Li, Shuaike Zhang, Kai Liu, Qi Chen, Enhong Artificial Intelligence Knowledge editing is a technique for efficiently and accurately updating the knowledge of large language models (LLMs) to alleviate obsolescence and correct errors. However, most existing methods overfit to specific models, causing edited knowledge to be discarded during each LLM update and requiring frequent re-editing, which is particularly burdensome in today's rapidly evolving open-source community. To address this issue, we propose the problem of cross-model knowledge editing and introduce MindBridge, a scalable solution inspired by the low coupling between modality processing and LLMs in multi-modal models. MindBridge introduces the novel concept of memory modality, which encodes edited knowledge as an independent modality. It first performs LLM-agnostic pre-training of the memory modality and then integrates it with various LLMs. Extensive experiments on multiple LLMs and popular knowledge editing datasets demonstrate that MindBridge achieves superior performance even in editing tens of thousands of knowledge entries and can flexibly adapt to different LLMs. Our code is available at https://github.com/CrashBugger/MindBridge. |
| title | MindBridge: Scalable and Cross-Model Knowledge Editing via Memory-Augmented Modality |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2503.02701 |