No article text was recorded for this version.
sequential editing collapse
Version 2 of 2143 papers215 conceptsfrozen 2026-10-04
Papers in this version
- Blog: LyapLock: Bounded Knowledge Preservation in Sequential Large Language Model Editing
- Blog: The Mirage of Model Editing: Revisiting Evaluation in the Wild
- Blog: The Butterfly Effect of Model Editing: Few Edits Can Trigger Large Language Models Collapse
- Blog: Editing Large Language Models: Problems, Methods, and Opportunities
- Blog: SAKE: Towards Editing Auditory Attribute Knowledge of Large Audio-Language Models
- Blog: Model Editing Harms General Abilities of Large Language Models: Regularization to the Rescue
- Blog: Multiplicative Orthogonal Sequential Editing for Language Models
- Blog: Rebuilding ROME : Resolving Model Collapse during Sequential Model Editing
- Blog: Navigating the Dual Facets: A Comprehensive Evaluation of Sequential Memory Editing in Large Language Models
- Blog: WilKE: Wise-Layer Knowledge Editor for Lifelong Knowledge Editing
- Blog: Editing Large Language Models: Problems, Methods, and Opportunities
- Blog: Understanding the Limits of Lifelong Knowledge Editing in LLMs
- Blog: LyapLock: Bounded Knowledge Preservation in Sequential Large Language Model Editing
- Blog: The Missing Piece in Model Editing: A Deep Dive into the Hidden Damage Brought By Model Editing
- Blog: Model Editing Can Hurt General Abilities of Large Language Models
- Blog: Potential and Challenges of Model Editing for Social Debiasing
- Blog: The Butterfly Effect of Model Editing: Few Edits Can Trigger Large Language Models Collapse
- Blog: Aging with GRACE: Lifelong Model Editing with Key-Value Adaptors
- Blog: Benchmarking and Rethinking Knowledge Editing for Large Language Models
- Blog: GNNs Also Deserve Editing, and They Need It More Than Once
- Blog: Mitigating Heterogeneous Token Overfitting in LLM Knowledge Editing
- Blog: Editing Across Languages: A Survey of Multilingual Knowledge Editing
- Blog: A Comprehensive Study of Knowledge Editing for Large Language Models
- Blog: Neuron Patching: Neuron-level Model Editing on Code Generation and LLMs
- Blog: Knowledge Editing for Large Language Models: A Survey
- Blog: Rethinking the Residual Distribution of Locate-then-Editing Methods in Model Editing
- Blog: DeltaEdit: Enhancing Sequential Editing in Large Language Models by Controlling Superimposed Noise
- Blog: Reasons and Solutions for the Decline in Model Performance after Editing
- Blog: Gradient Rewiring for Editable Graph Neural Network Training
- Blog: Should We Really Edit Language Models? On the Evaluation of Edited Language Models
- Blog: ConceptEdit: Conceptualization-Augmented Knowledge Editing in Large Language Models for Commonsense Reasoning
- Blog: REPAIR: Robust Editing via Progressive Adaptive Intervention and Reintegration
- Blog: Gradient Rewiring for Editable Graph Neural Network Training
- Blog: Consecutive Model Editing with Batch alongside HooK Layers
- Blog: Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors
- Blog: NAACL2025 Tutorial: Adaptation of Large Language Models
- Blog: MedMKEB: A Comprehensive Knowledge Editing Benchmark for Medical Multimodal Large Language Models
- Blog: MultiMedEdit: A Scenario-Aware Benchmark for Evaluating Knowledge Editing in Medical VQA
- Blog: Do Language Models Have Beliefs? Methods for Detecting, Updating, and Visualizing Model Beliefs
- Blog: Model Editing at Scale leads to Gradual and Catastrophic Forgetting
- Blog: WilKE: Wise-Layer Knowledge Editor for Lifelong Knowledge Editing
- Blog: In-Context Editing: Learning Knowledge from Self-Induced Distributions
- Blog: QueueEDIT: Structural Self-Correction for Sequential Model Editing in LLMs
- Blog: Model Merging for Knowledge Editing
- Blog: Towards Lifelong Model Editing via Simulating Ideal Editor
- Blog: WikiBigEdit: Understanding the Limits of Lifelong Knowledge Editing in LLMs
- Blog: Knowledge Editing in Language Models via Adapted Direct Preference Optimization
- Blog: Editing as Unlearning: Are Knowledge Editing Methods Strong Baselines for Large Language Model Unlearning?
- Blog: RuleEdit: Towards Rule-Level Knowledge Generalization to Mitigate Over-Editing in Large Language Models
- Blog: Minimal, Local, and Robust: Embedding-Only Edits for Implicit Bias in T2I Models
- Blog: AnyEdit: Edit Any Knowledge Encoded in Language Models
- Blog: The Fall of ROME: Understanding the Collapse of LLMs in Model Editing
- Blog: Navigating the Dual Facets: A Comprehensive Evaluation of Sequential Memory Editing in Large Language Models
- Blog: Towards Teachable Reasoning Systems: Using a Dynamic Memory of User Feedback for Continual System Improvement
- Blog: WISE: Rethinking the Knowledge Memory for Lifelong Model Editing of Large Language Models
- Blog: In-Context Editing: Learning Knowledge from Self-Induced Distributions
- Blog: BABELEDITS: A Benchmark and a Modular Approach for Robust Cross-lingual Knowledge Editing of Large Language Models
- Blog: Towards Comprehensive and Efficient Post Safety Alignment of Large Language Models via Safety Patching
- Blog: Language Anisotropic Cross-Lingual Model Editing
- Blog: Fast-Slow Test-Time Adaptation for Online Vision-and-Language Navigation
Showing 60 of 143 papers.
History & citation
Current · Permanent link
- Scaling Sequential Model Editing for Lifelong Knowledge Updates merged into this direction (62% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_sequential_editing_collapse_994b74e8,
title = {sequential editing collapse},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/sequential-editing-collapse/rdr_994b74e881544e0a9cfa818e1240d9f8},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-22},
}This exact version (version 2, frozen text):
@misc{lacuna_sequential_editing_collapse_994b74e8_v2,
title = {sequential editing collapse},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/sequential-editing-collapse/rdr_994b74e881544e0a9cfa818e1240d9f8/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-22},
}