Knowledge editing has emerged as a lightweight alternative to retraining for correcting or injecting specific facts in large language models (LLMs). Meanwhile, fine-tuning remains the default operation for adapting LLMs to new domains and tasks. Despite their widespread adoption, these two post-training interventions have been studied in isolation, leaving open a crucial question: if we fine-tune an edited model, do the edits survive? This question is motivated by two practical scenarios: removing covert or malicious edits, and preserving beneficial edits. If fine-tuning impairs edits (Fig.1), current KE methods become less useful, as every fine-tuned model would require re-editing, which significantly increases the cost; if edits persist, fine-tuned models risk propagating hidden malicious edits, raising serious safety concerns. To this end, we systematically quantify edit decay after fine-tuning, investigating how fine-tuning affects knowledge editing. Our results show that edits decay after fine-tuning, with survival varying across configurations, e.g., AlphaEdit edits decay more than MEMIT edits. Further, we find that fine-tuning edited layers only can effectively remove edits, though at a slight cost to downstream performance. Surprisingly, fine-tuning non-edited layers impairs more edits than full fine-tuning. Overall, our study establishes empirical baselines and actionable strategies for integrating knowledge editing with fine-tuning, and underscores that evaluating model editing requires considering the full LLM application pipeline.

Sequential knowledge editing techniques aim to continuously update knowledge in large language models at low cost, preventing models from generating outdated or incorrect information. However, existing sequential editing methods suffer from a significant decline in editing success rates after long-term editing. Through theoretical analysis and experiments, our findings reveal that as the number of edits increases, the model's output increasingly deviates from the desired target, leading to a drop in editing success rates. We refer to this issue as the superimposed noise accumulation problem. Our further analysis demonstrates that the problem is related to the erroneous activation of irrelevant knowledge and conflicts between activated knowledge. Based on this analysis, a method named DeltaEdit is proposed that reduces conflicts between knowledge through dynamic orthogonal constraint strategies. Experiments show that DeltaEdit significantly reduces superimposed noise, achieving a 16.8% improvement in editing performance over the strongest baseline.

Large language models (LLMs) are increasingly used in software development. However, while LLMs remain static after pretraining, programming languages and APIs continue to evolve, leading to the generation of deprecated or incompatible code that undermines reliability. Retraining LLMs from scratch to reflect such changes is computationally expensive, making model editing a promising lightweight alternative that updates only a small subset of parameters. Despite its potential, it remains unclear whether model editing yields genuine syntactic and semantic adaptations or merely superficial fixes. In this work, we present a systematic study of five state-of-the-art model editing methods: Constrained Fine-Tuning (FT), GRACE, MEMIT, PMET, and ROME. We apply these methods to three leading open-source code LLMs, CodeLlama, CodeQwen1.5, and DeepSeek-Coder, under controlled API deprecation scenarios. Our evaluation covers both instant and sequential editing settings, using three disjoint evaluation sets designed to assess reliability, generalization, and specificity. We measure model correctness at three levels: successful compilation, partial test case pass, and full test pass. Our findings show that instant edits consistently degrade model performance, with syntactic validity dropping by up to 86 percentage points and functional correctness declining by 45 points even in the best-performing setting. Sequential edits further amplify this degradation, and in some cases, model performance collapses entirely. Across all models, most passing generations relied on workarounds rather than correctly adopting the intended changes, while faulty adoptions that result in test failures or compilation errors were significantly more frequent. Correct adoptions, where the model correctly integrates the intended change, occurred in only about 6% of cases.

While Knowledge Editing (KE) has been widely explored in English, its behavior in morphologically rich languages like Arabic remains underexamined. In this work, we present the first study of Arabic KE. We evaluate four methods (ROME, MEMIT, ICE, and LTE) on Arabic translations of the ZsRE and Counterfact benchmarks, analyzing both multilingual and cross-lingual settings. Our experiments on Llama-2-7B-chat show that parameter-based methods struggle with cross-lingual generalization, while instruction-tuned methods perform more robustly. We extend Learning-To-Edit (LTE) to a multilingual setting and show that joint Arabic-English training improves both editability and transfer. We release Arabic KE benchmarks and multilingual training for LTE data to support future research.

Knowledge editing, which aims to update the knowledge encoded in language models, can be deceptive. Despite the fact that many existing knowledge editing algorithms achieve near-perfect performance on conventional metrics, the models edited by them are still prone to generating original knowledge. This paper introduces the concept of "superficial editing" to describe this phenomenon. Our comprehensive evaluation reveals that this issue presents a significant challenge to existing algorithms. Through systematic investigation, we identify and validate two key factors contributing to this issue: (1) the residual stream at the last subject position in earlier layers and (2) specific attention modules in later layers. Notably, certain attention heads in later layers, along with specific left singular vectors in their output matrices, encapsulate the original knowledge and exhibit a causal relationship with superficial editing. Furthermore, we extend our analysis to the task of superficial unlearning, where we observe consistent patterns in the behavior of specific attention heads and their corresponding left singular vectors, thereby demonstrating the robustness and broader applicability of our methodology and conclusions. Our code is available here.

Knowledge editing aims to update outdated information in Large Language Models (LLMs). A representative line of study is locate-then-edit methods, which typically employ causal tracing to identify the modules responsible for recalling factual knowledge about entities. However, we find these methods are often sensitive only to changes in the subject entity, leaving them less effective at adapting to changes in relations. This limitation results in poor editing locality, which can lead to the persistence of irrelevant or inaccurate facts, ultimately compromising the reliability of LLMs. We believe this issue arises from the insufficient precision of knowledge localization. To address this, we propose a Fine-grained Neuron-level Knowledge Editing (FiNE) method that enhances editing locality without affecting overall success rates. By precisely identifying and modifying specific neurons within feed-forward networks, FiNE significantly improves knowledge localization and editing. Quantitative experiments demonstrate that FiNE efficiently achieves better overall performance compared to existing techniques, providing new insights into the localization and modification of knowledge within LLMs. Recently, various methods for the precise editing of outdated or wrong knowledge within Large Language Models (LLMs) (Touvron et al., 2023a;b; Jiang et al., 2024; Dubey et al., 2024) have been proposed (Mazzia et al., 2023; Yao et al., 2023; Wang et al., 2023). This paper primarily focuses on locate-then-edit methods, which have emerged as a promising and mainstream approach for knowledge editing in LLMs. A key representative of these approaches is ROME (Meng et al., 2022), which employs causal tracing to identify specific modules responsible for recalling facts about subject entities.

Large Language Models (LLMs) are used in various downstream language tasks, making it crucial to keep their knowledge up-to-date, but both retraining and fine-tuning the model can be costly. Model editing offers an efficient and effective alternative by a single update to only a key subset of model parameters. While being efficient, these methods are not perfect. Sometimes knowledge edits are unsuccessful, i.e., UnderEdit, or the edit contaminated neighboring knowledge that should remain unchanged, i.e., OverEdit. To address these limitations, we propose iterative model editing, based on our hypothesis that a single parameter update is often insufficient, to mitigate UnderEdit, and neighbor-assisted model editing, which incorporates neighboring knowledge during editing to minimize OverEdit. Extensive experiments demonstrate that our methods effectively reduce UnderEdit up to 38 percentage points and OverEdit up to 6 percentage points across multiple model editing algorithms, LLMs, and benchmark datasets.

Large language models (LLMs) struggle with hallucinations due to false or outdated knowledge. Given the high resource demands of retraining these models, there is an increasing focus on developing model editing. However, the general abilities of LLMs across downstream tasks are prone to significant degradation during sequential editing. This paper statistically observes that the parameter matrix after editing exhibits a significant deviation compared to its previous state as the number of edits increases. This serious deviation affects the original knowledge associations within LLMs and leads to the degradation of their general abilities. To this end, a framework termed Editing Anchor Compression (EAC) is proposed to constrain the deviation of the parameter matrix during sequential editing. It compresses the editing information by selecting editing anchors that are important in encoding new relations without deviating too much from the original matrix, thereby preserving the general abilities. Experiments of applying EAC to two popular editing methods on three LLMs across four tasks are conducted. Evaluation results show that EAC effectively minimizes unreasonable deviations caused by model editing, preserving over 70% of the general abilities while better retaining the editing knowledge compared to the original counterpart methods.