Disentangling Knowledge Representations for Large Language Model Editing
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917360298885120 |
|---|---|
| author | Zhang, Mengqi Zhou, Zisheng Ye, Xiaotian Liu, Qiang Ren, Zhaochun Chen, Zhumin Ren, Pengjie |
| author_facet | Zhang, Mengqi Zhou, Zisheng Ye, Xiaotian Liu, Qiang Ren, Zhaochun Chen, Zhumin Ren, Pengjie |
| contents | Knowledge Editing has emerged as a promising solution for efficiently updating embedded knowledge in large language models (LLMs). While existing approaches demonstrate effectiveness in integrating new knowledge and preserving the original capabilities of LLMs, they fail to maintain fine-grained irrelevant knowledge, namely facts that share the same subject as edited knowledge but differ in relation and object. This challenge arises because subject representations inherently encode multiple attributes, causing the target and fine-grained irrelevant knowledge to become entangled in the representation space, and thus vulnerable to unintended alterations during editing. To address this, we propose DiKE, a novel approach that Disentangles Knowledge representations for LLM Editing (DiKE). DiKE consists of two key components: a Knowledge Representation Disentanglement (KRD) module that decomposes the subject representation into target-knowledge-related and -unrelated components, and a Disentanglementbased Knowledge Edit (DKE) module that updates only the target-related component while explicitly preserving the unrelated one. We further derive a closedform, rank-one parameter update based on matrix theory to enable efficient and minimally invasive edits. To rigorously evaluate fine-grained irrelevant knowledge preservation, we construct FINE-KED, a new benchmark comprising fine-grained irrelevant knowledge at different levels of relational similarity to the edited knowledge. Extensive experiments across multiple LLMs demonstrate that DiKE substantially improves fine-grained irrelevant knowledge preservation while maintaining competitive general editing performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_18774 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Disentangling Knowledge Representations for Large Language Model Editing Zhang, Mengqi Zhou, Zisheng Ye, Xiaotian Liu, Qiang Ren, Zhaochun Chen, Zhumin Ren, Pengjie Computation and Language Knowledge Editing has emerged as a promising solution for efficiently updating embedded knowledge in large language models (LLMs). While existing approaches demonstrate effectiveness in integrating new knowledge and preserving the original capabilities of LLMs, they fail to maintain fine-grained irrelevant knowledge, namely facts that share the same subject as edited knowledge but differ in relation and object. This challenge arises because subject representations inherently encode multiple attributes, causing the target and fine-grained irrelevant knowledge to become entangled in the representation space, and thus vulnerable to unintended alterations during editing. To address this, we propose DiKE, a novel approach that Disentangles Knowledge representations for LLM Editing (DiKE). DiKE consists of two key components: a Knowledge Representation Disentanglement (KRD) module that decomposes the subject representation into target-knowledge-related and -unrelated components, and a Disentanglementbased Knowledge Edit (DKE) module that updates only the target-related component while explicitly preserving the unrelated one. We further derive a closedform, rank-one parameter update based on matrix theory to enable efficient and minimally invasive edits. To rigorously evaluate fine-grained irrelevant knowledge preservation, we construct FINE-KED, a new benchmark comprising fine-grained irrelevant knowledge at different levels of relational similarity to the edited knowledge. Extensive experiments across multiple LLMs demonstrate that DiKE substantially improves fine-grained irrelevant knowledge preservation while maintaining competitive general editing performance. |
| title | Disentangling Knowledge Representations for Large Language Model Editing |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2505.18774 |