Navigating the Dual Facets: A Comprehensive Evaluation of Sequential Memory Editing in Large Language Models (2024.acl-long)
Copied to clipboard
Zihao Lin, Mohammad Beigi, Hongxuan Li, Yufan Zhou, Yuxiang Zhang, Qifan Wang, Wenpeng Yin, Lifu Huang
| Challenge: | Memory Editing (ME) has emerged as an efficient method to modify erroneous facts or inject new knowledge into Large Language Models (LLMs). |
| Approach: | They propose to evaluate LLMs with single edit only and parameter-modifying ME with parameter-preserving ME. |
| Outcome: | The proposed method can maintain LLMs’ fundamental capabilities but struggles to accurately recall edited knowledge presented in a different format. |
Similar Papers
Editing the Mind of Giants: An In-Depth Exploration of Pitfalls of Knowledge Editing in Large Language Models (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Knowledge editing is a promising technique for updating factual knowledge in large language models (LLMs) but studies have identified side effects such as knowledge distortion and the deterioration of general abilities that have emerged after editing. |
| Approach: | They propose to evaluate the side effects of knowledge editing in large language models using metrics and benchmarks. |
| Outcome: | The results of the study highlight the limitations of current knowledge editing methods and outline potential research directions. |
Neuron-Level Sequential Editing for Large Language Models (2025.acl-long)
Copied to clipboard
Houcheng Jiang, Junfeng Fang, Tianyu Zhang, Baolong Bi, An Zhang, Ruipeng Wang, Tao Liang, Xiang Wang
| Challenge: | Existing model editing methods focus on single-round editing and often face significant challenges in sequential model editing. |
| Approach: | They propose a model editing method that optimizes the target layer’s hidden states using the model’s original weights to prevent model failure. |
| Outcome: | The proposed method outperforms existing model editing methods and is available on the open-source platform 4open.science. |
The Model Agreed, But Didn’t Learn: Diagnosing Surface Compliance in Large Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models internalize vast world knowledge as parametric memory, yet inherit the staleness and errors of their source corpora. |
| Approach: | They propose a framework that subjects models to discriminative self-assessment under diverse contextual pressures to scrutinize subtle behavioral nuances induced by memory modifications. |
| Outcome: | The proposed framework achieves high benchmarks without overwriting internal beliefs, while recursive modifications accumulate representational residues, triggering cognitive instability and permanently diminishing the reversibility of the model’s memory state. |
Editing Large Language Models: Problems, Methods, and Opportunities (2023.emnlp-main)
Copied to clipboard
Yunzhi Yao, Peng Wang, Bozhong Tian, Siyuan Cheng, Zhoubo Li, Shumin Deng, Huajun Chen, Ningyu Zhang
| Challenge: | Recent advances in model editing for LLMs have created challenges and opportunities for the community. |
| Approach: | They propose to alter the behavior of LLMs efficiently within a specific domain without negatively impacting performance across other inputs. |
| Outcome: | The proposed method alters behavior of LLMs efficiently within a specific domain without negatively impacting performance across other inputs. |
QueueEDIT: Structural Self-Correction for Sequential Model Editing in LLMs (2026.findings-acl)
Copied to clipboard
| Challenge: | Recent studies have shown that large language models (LLMs) can be effective for correcting factual inaccuracies but can still suffer from hallucinations. |
| Approach: | They propose a queue-based self-correction framework that addresses parameter bias during sequential model editing. |
| Outcome: | The proposed framework outperforms baseline models while maintaining competitive performance in single-turn editing. |
On the Robustness of Editing Large Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies have exhibited impressive success and significant potential. |
| Approach: | They propose to modify the knowledge memory with minimum computational cost while preserving the performance on the retained knowledge. |
| Outcome: | The proposed methods avoid retraining to update the model parameters and have demonstrated promising performance and efficiency. |
Can We Continually Edit Language Models? On the Knowledge Attenuation in Sequential Model Editing (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for model editing suffer from knowledge attenuation due to redundant parameters interference and update weight disentanglement. |
| Approach: | They propose a method to mitigate the problem of knowledge attenuation in sequential editing by analyzing redundant parameters interference and update weight disentanglement. |
| Outcome: | The proposed method mitigates the knowledge attenuation issue and improves on existing benchmarks. |
Model Surgery: Modulating LLM’s Behavior Via Simple Parameter Editing (2025.naacl-long)
Copied to clipboard
| Challenge: | Current approaches for detoxification or preventing jailbreaking involve fine-tuning billions of parameters through gradient descent with substantial computational cost. |
| Approach: | They propose to use supervised fine-tuning and Reinforcement Learning from human feedback to modify LLMs' behavior by directly editing a small subset of parameters. |
| Outcome: | Experiments show that editing a small subset of parameters can modulate specific behaviors of LLMs, such as detoxification and resistance to jailbreak, with only inference-level computational resources. |
Model Editing at Scale leads to Gradual and Catastrophic Forgetting (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing model editing methods are evaluated using metrics for reliability, specificity and generalization over one or few edits. |
| Approach: | They evaluate model editing methods for three crucial properties - editing proficiency, fact forgetting and downstream performance. |
| Outcome: | The proposed methods are based on two state-of-the-art models - ROME and MEMIT. |
Editing Conceptual Knowledge for Large Language Models (2024.findings-emnlp)
Copied to clipboard
Xiaohan Wang, Shengyu Mao, Shumin Deng, Yunzhi Yao, Yue Shen, Lei Liang, Jinjie Gu, Huajun Chen, Ningyu Zhang
| Challenge: | Existing knowledge editing methods can modify concept-level definitions, but they can distort instantial knowledge in LLMs, leading to poor performance. |
| Approach: | They construct a benchmark dataset ConceptEdit and establish new metrics for evaluation to investigate the editing capability of LLMs. |
| Outcome: | The proposed methods can modify concept definitions but can distort instantial knowledge in LLMs, leading to poor performance. |