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

arXiv: https://arxiv.org/abs/2211.11031 · HTML: https://mlsanity.com/paper/2211.11031/

## Key facts

- Cited by 271 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 49 references that are in the map.
- First posted on arXiv 20 Nov 2022.

## Builds on (most cited first, 30 of 36)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [Scaling Language Models: Methods, Analysis & Insights from Training Gopher](https://mlsanity.com/paper/2112.11446/) (2021)
- [Experience Replay for Continual Learning](https://mlsanity.com/paper/1811.11682/) (2018)
- [Mass-Editing Memory in a Transformer](https://mlsanity.com/paper/2210.07229/) (2022)
- [Learning to Prompt for Continual Learning](https://mlsanity.com/paper/2112.08654/) (2021)
- [Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval](https://mlsanity.com/paper/2007.00808/) (2020)
- [How Much Knowledge Can You Pack Into the Parameters of a Language Model?](https://mlsanity.com/paper/2002.08910/) (2020)
- [DualPrompt: Complementary Prompting for Rehearsal-free Continual Learning](https://mlsanity.com/paper/2204.04799/) (2022)
- [Editing Factual Knowledge in Language Models](https://mlsanity.com/paper/2104.08164/) (2021)
- [Fast Model Editing at Scale](https://mlsanity.com/paper/2110.11309/) (2021)
- [Memory-Based Model Editing at Scale](https://mlsanity.com/paper/2206.06520/) (2022)
- [Zero-Shot Relation Extraction via Reading Comprehension](https://mlsanity.com/paper/1706.04115/) (2017)
- [ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection](https://mlsanity.com/paper/2203.09509/) (2022)
- [Online Continual Learning with Maximally Interfered Retrieval](https://mlsanity.com/paper/1908.04742/) (2019)
- [Memory Networks](https://mlsanity.com/paper/1410.3916/) (2014)
- [Post-Training Quantization for Vision Transformer](https://mlsanity.com/paper/2106.14156/) (2021)
- [Mind the Gap: Assessing Temporal Generalization in Neural Language Models](https://mlsanity.com/paper/2102.01951/) (2021)
- [Modifying Memories in Transformer Models](https://mlsanity.com/paper/2012.00363/) (2020)
- [Surgical Fine-Tuning Improves Adaptation to Distribution Shifts](https://mlsanity.com/paper/2210.11466/) (2022)
- [Editable Neural Networks](https://mlsanity.com/paper/2004.00345/) (2020)
- [Mixout: Effective Regularization to Finetune Large-scale Pretrained Language Models](https://mlsanity.com/paper/1909.11299/) (2019)
- [Do Language Models Have Beliefs? Methods for Detecting, Updating, and Visualizing Model Beliefs](https://mlsanity.com/paper/2111.13654/) (2021)
- [On Transferability of Prompt Tuning for Natural Language Processing](https://mlsanity.com/paper/2111.06719/) (2021)
- [FairLex: A Multilingual Benchmark for Evaluating Fairness in Legal Text Processing](https://mlsanity.com/paper/2203.07228/) (2022)

## Built on by (most cited first, 30 of 271)

- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [Editing Large Language Models: Problems, Methods, and Opportunities](https://mlsanity.com/paper/2305.13172/) (2023)
- [Challenges and Applications of Large Language Models](https://mlsanity.com/paper/2307.10169/) (2023)
- [AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models](https://mlsanity.com/paper/2410.02355/) (2024)
- [Continual Learning of Large Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2404.16789/) (2024)
- [Knowledge Editing for Large Language Models: A Survey](https://mlsanity.com/paper/2310.16218/) (2023)
- [A Comprehensive Study of Knowledge Editing for Large Language Models](https://mlsanity.com/paper/2401.01286/) (2024)
- [Continual Learning with Pre-Trained Models: A Survey](https://mlsanity.com/paper/2401.16386/) (2024)
- [MemOS: A Memory OS for AI System](https://mlsanity.com/paper/2507.03724/) (2025)
- [EasyEdit: An Easy-to-use Knowledge Editing Framework for Large Language Models](https://mlsanity.com/paper/2308.07269/) (2023)
- [BadEdit: Backdooring large language models by model editing](https://mlsanity.com/paper/2403.13355/) (2024)
- [From Matching to Generation: A Survey on Generative Information Retrieval](https://mlsanity.com/paper/2404.14851/) (2024)
- [Detoxifying Large Language Models via Knowledge Editing](https://mlsanity.com/paper/2403.14472/) (2024)
- [MELO: Enhancing Model Editing with Neuron-Indexed Dynamic LoRA](https://mlsanity.com/paper/2312.11795/) (2023)
- [AnyEdit: Edit Any Knowledge Encoded in Language Models](https://mlsanity.com/paper/2502.05628/) (2025)
- [MoRAL: MoE Augmented LoRA for LLMs' Lifelong Learning](https://mlsanity.com/paper/2402.11260/) (2024)
- [MyVLM: Personalizing VLMs for User-Specific Queries](https://mlsanity.com/paper/2403.14599/) (2024)
- [Larimar: Large Language Models with Episodic Memory Control](https://mlsanity.com/paper/2403.11901/) (2024)
- [A Comprehensive Survey of Large Language Models and Multimodal Large Language Models in Medicine](https://mlsanity.com/paper/2405.08603/) (2024)
- [Can We Edit Multimodal Large Language Models?](https://mlsanity.com/paper/2310.08475/) (2023)
- [Learning to Edit: Aligning LLMs with Knowledge Editing](https://mlsanity.com/paper/2402.11905/) (2024)
- [WilKE: Wise-Layer Knowledge Editor for Lifelong Knowledge Editing](https://mlsanity.com/paper/2402.10987/) (2024)
- [Lifelong Knowledge Editing for LLMs with Retrieval-Augmented Continuous Prompt Learning](https://mlsanity.com/paper/2405.03279/) (2024)
- [Knowledge Boundary of Large Language Models: A Survey](https://mlsanity.com/paper/2412.12472/) (2024)
- [AKEW: Assessing Knowledge Editing in the Wild](https://mlsanity.com/paper/2402.18909/) (2024)
- [Multi-hop Question Answering under Temporal Knowledge Editing](https://mlsanity.com/paper/2404.00492/) (2024)
- [Online Adaptation of Language Models with a Memory of Amortized Contexts](https://mlsanity.com/paper/2403.04317/) (2024)
- [MemLLM: Finetuning LLMs to Use An Explicit Read-Write Memory](https://mlsanity.com/paper/2404.11672/) (2024)
- [Evaluating the Reversal Curse in Model Editing](https://mlsanity.com/paper/2310.10322/) (2023)
- [A Survey on Knowledge Editing of Neural Networks](https://mlsanity.com/paper/2310.19704/) (2023)

## Abstract (arXiv)

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}.