WilKE: Wise-Layer Knowledge Editor for Lifelong Knowledge Editing
- URL: http://arxiv.org/abs/2402.10987v2
- Date: Wed, 5 Jun 2024 07:44:30 GMT
- Title: WilKE: Wise-Layer Knowledge Editor for Lifelong Knowledge Editing
- Authors: Chenhui Hu, Pengfei Cao, Yubo Chen, Kang Liu, Jun Zhao,
- Abstract summary: This study reveals a performance degradation encountered by knowledge editing in lifelong editing.
We introduce a knowledge editing approach named Wise-Layer Knowledge Editor (WilKE)
WilKE selects editing layer based on the pattern matching degree of editing knowledge across different layers in language models.
- Score: 19.357663224043534
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Knowledge editing aims to rectify inaccuracies in large language models (LLMs) without costly retraining for outdated or erroneous knowledge. However, current knowledge editing methods primarily focus on single editing, failing to meet the requirements for lifelong editing. This study reveals a performance degradation encountered by knowledge editing in lifelong editing, characterized by toxicity buildup and toxicity flash, with the primary cause identified as pattern unmatch. We introduce a knowledge editing approach named Wise-Layer Knowledge Editor (WilKE), which selects editing layer based on the pattern matching degree of editing knowledge across different layers in language models. Experimental results demonstrate that, in lifelong editing, WilKE exhibits an average improvement of 46.2% and 67.8% on editing GPT2-XL and GPT-J relative to state-of-the-art knowledge editing methods.
Related papers
- K-Edit: Language Model Editing with Contextual Knowledge Awareness [71.73747181407323]
Knowledge-based model editing enables precise modifications to the weights of large language models.
We present K-Edit, an effective approach to generating contextually consistent knowledge edits.
arXiv Detail & Related papers (2025-02-15T01:35:13Z) - AnyEdit: Edit Any Knowledge Encoded in Language Models [69.30638272162267]
We propose AnyEdit, a new autoregressive editing paradigm for large language models (LLMs)
It decomposes long-form knowledge into sequential chunks and iteratively edits the key token in each chunk, ensuring consistent and accurate outputs.
It outperforms strong baselines by 21.5% on benchmarks including UnKEBench, AKEW, and our new EditEverything dataset for long-form diverse-formatted knowledge.
arXiv Detail & Related papers (2025-02-08T16:18:37Z) - Related Knowledge Perturbation Matters: Rethinking Multiple Pieces of Knowledge Editing in Same-Subject [49.559994791305535]
Current state-of-the-art editing methods struggle when tasked with editing multiple related knowledge pieces for the same subject.
We introduce the $textS2textRKE$(Same-Subject Related Knowledge Editing) benchmark.
Our experiments reveal that only mainstream locate-then-edit methods, such as ROME and MEMIT, exhibit "related knowledge perturbation"
arXiv Detail & Related papers (2025-02-08T04:47:17Z) - Lifelong Sequential Knowledge Editing without Model Degradation [11.14177136208272]
We show that locate-then-edit knowledge editing methods lead to overfitting on the edited facts.
We show that continuous knowledge editing using these methods leads to disproportionate growth in the norm of the edited matrix.
We present ENCORE - Early stopping and Norm-Constrained Robust knowledge Editing.
arXiv Detail & Related papers (2025-02-03T18:59:14Z) - AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models [65.93240009586351]
Large language models (LLMs) often exhibit hallucinations due to incorrect or outdated knowledge.
We introduce AlphaEdit, a novel solution that projects perturbation onto the null space of the preserved knowledge before applying it to the parameters.
We theoretically prove that this projection ensures the output of post-edited LLMs remains unchanged when queried about the preserved knowledge.
arXiv Detail & Related papers (2024-10-03T10:06:27Z) - Knowledge in Superposition: Unveiling the Failures of Lifelong Knowledge Editing for Large Language Models [19.357663224043534]
Knowledge editing aims to update outdated or incorrect knowledge in large language models.
Current knowledge editing methods have limited scalability for lifelong editing.
This study explores the fundamental reason why knowledge editing fails in lifelong editing.
arXiv Detail & Related papers (2024-08-14T09:43:32Z) - Editing the Mind of Giants: An In-Depth Exploration of Pitfalls of Knowledge Editing in Large Language Models [26.516571783335824]
Recent studies have identified side effects, such as knowledge distortion and the deterioration of general abilities, that have emerged after editing.
This survey presents a comprehensive study of these side effects, providing a unified perspective on the challenges of knowledge editing in large language models.
arXiv Detail & Related papers (2024-06-03T15:28:21Z) - Knowledge Graph Enhanced Large Language Model Editing [37.6721061644483]
Large language models (LLMs) are pivotal in advancing natural language processing (NLP) tasks.
Existing editing methods struggle to track and incorporate changes in knowledge associated with edits.
We propose a novel model editing method that leverages knowledge graphs for enhancing LLM editing, namely GLAME.
arXiv Detail & Related papers (2024-02-21T07:52:26Z) - On the Robustness of Editing Large Language Models [57.477943944826904]
Large language models (LLMs) have played a pivotal role in building communicative AI, yet they encounter the challenge of efficient updates.
This work seeks to understand the strengths and limitations of editing methods, facilitating practical applications of communicative AI.
arXiv Detail & Related papers (2024-02-08T17:06:45Z) - EasyEdit: An Easy-to-use Knowledge Editing Framework for Large Language Models [45.70959260613425]
We propose EasyEdit, an easy-to-use knowledge editing framework for Large Language Models.
It supports various cutting-edge knowledge editing approaches and can be readily applied to many well-known LLMs.
We report the knowledge editing results on LlaMA-2 with EasyEdit, demonstrating that knowledge editing surpasses traditional fine-tuning.
arXiv Detail & Related papers (2023-08-14T16:52:42Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.