paper-with-me

홈 › Papers

Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors

2022-11-20 · NeurIPS 2023 11 · Thomas Hartvigsen, Swami Sankaranarayanan, Hamid Palangi, Yoon Kim, Marzyeh Ghassemi

Deployed language models decay over time due to shifting inputs, changing user needs, or emergent world-knowledge gaps. When such problems are identified, we want to make targeted edits while avoiding expensive retraining. However, current model editors, which modify such behaviors of pre-trained models, degrade model performance quickly across multiple, sequential edits. We propose GRACE, a lifelong model editing method, which implements spot-fixes on streaming errors of a deployed model, ensuring minimal impact on unrelated inputs. GRACE writes new mappings into a pre-trained model's latent space, creating a discrete, local codebook of edits without altering model weights. This is the first method enabling thousands of sequential edits using only streaming errors. Our experiments on T5, BERT, and GPT models show GRACE's state-of-the-art performance in making and retaining edits, while generalizing to unseen inputs. Our code is available at https://www.github.com/thartvigsen/grace}.

📄 PDF Abstract BibTeX arXiv:2211.11031

Code (1)

thartvigsen/grace 공식 구현 pytorch

Tasks

Model EditingWorld Knowledge

Similar Papers 제목 키워드 기반

ELDER: Enhancing Lifelong Model Editing with Mixture-of-LoRA

2024-08-19 · Jiaang Li, Quan Wang, Zhongnan Wang, Yongdong Zhang 외

Large language models (LLMs) require model editing to efficiently update specific knowledge within them and avoid factual errors. Most model editing methods are solely designed for single-time use and result in a signifi…

Model Editing

Edit Less, Achieve More: Dynamic Sparse Neuron Masking for Lifelong Knowledge Editing in LLMs

2025-10-25 · Jinzhe Liu, Junshu Sun, Shufan Shen, Chenxue Yang 외 arxiv

Lifelong knowledge editing enables continuous, precise updates to outdated knowledge in large language models (LLMs) without computationally expensive full retraining. However, existing methods often accumulate errors th…

knowledge editing

LEMoE: Advanced Mixture of Experts Adaptor for Lifelong Model Editing of Large Language Models

2024-06-28 · Renzhi Wang, Piji Li

Large language models (LLMs) require continual knowledge updates to stay abreast of the ever-changing world facts, prompting the formulation of lifelong model editing task. While recent years have witnessed the developme…

Mixture-of-ExpertsModel Editing

WilKE: Wise-Layer Knowledge Editor for Lifelong Knowledge Editing

2024-02-16 · Chenhui Hu, Pengfei Cao, Yubo Chen, Kang Liu 외

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, …

knowledge editing

Lifelong Knowledge Editing for Vision Language Models with Low-Rank Mixture-of-Experts

2024-11-23 · CVPR 2025 1 · Qizhou Chen, Chengyu Wang, Dakan Wang, Taolin Zhang 외

Model editing aims to correct inaccurate knowledge, update outdated information, and incorporate new data into Large Language Models (LLMs) without the need for retraining. This task poses challenges in lifelong scenario…

knowledge editingMixture-of-ExpertsModel Editing