Knowledge Editing

Efficiently updating Large Language Models (LLMs) with new or evolving factual knowledge remains a central challenge, as even parameter-efficient adaptation can erode previously acquired reasoning abilities. This tension reflects a plasticity-stability dilemma: models must incorporate new knowledge while preserving skill-critical representations. In this work, we study this trade-off through the spectral structure of multilayer perceptron weight matrices. We show, both theoretically and empirically, that information essential for reasoning is not localized only in dominant singular directions, but is instead distributed across the singular spectrum. Motivated by this observation, we introduce PALoRA, a two-stage framework for knowledge injection with reduced interference. PALoRA first trains a Singular Value Fine-Tuning (SVF) expert on a reasoning dataset and uses its learned singular scaling vector as a frozen geometric probe to identify components that are critical for the target skill. It then performs factual knowledge injection with Low-Rank Adaptation (LoRA) under a structural orthogonality constraint, ensuring that updates avoid the identified skill-relevant subspace. Across Llama 3.1 8B and Mistral 7B, and across mathematical, coding, and scientific reasoning benchmarks, PALoRA preserves on average 95% of the SVF expert's reasoning performance while maintaining competitive factual recall. It consistently improves skill retention over prior spectral Parameter-Efficient Fine-Tuning (PEFT) methods while adding less than 0.006% parameter overhead.

Knowledge editing (KE) provides a lightweight alternative to repeated fine-tuning of LLMs. However, most existing KE methods target dense feed-forward layers, while modern LLMs increasingly adopt Mixture-of-Experts (MoE) architectures for their superior memory footprint and inference efficiency. This mismatch leaves a growing class of production models without principled editing tools. We propose a MEMIT-like framework for knowledge editing in MoE-based LLMs. Our method exploits the tensor structure of MoE layers to formulate the editing objective faithfully at the per expert level, and applies the Woodbury matrix identity to avoid materializing or inverting the full stacked matrix of expert weights. The resulting update reduces to inversions of fixed low-rank matrices and requires no additional backward passes. Empirically, our approach matches the editing quality of strong baselines on the main KE metrics while accelerating the editing procedure by up to 6x, owing to the batched MEMIT-style formulation and the low-dimensional inversions enabled by the Woodbury identity. These results show that closed-form, parameter-modifying KE can be extended efficiently beyond dense layers, opening a path toward scalable knowledge editing in modern sparse LLM architectures.

Multilingual knowledge editing (MKE) remains challenging because language-specific edits interfere with one another, even when locate-then-edit methods work well in monolingual settings. This paper focuses on three issues: the effectiveness of vector merging methods for MKE, the extent to which Task Singular Vectors for Merging (TSVM) can reduce multilingual interference, and the influence of the weight scaling factor and rank compression ratio on performance. We evaluate six merging variants with two popular backbone large language models, two base knowledge editing methods, and 12 languages on the MzsRE benchmark under a large-scale batch-editing setting. Our results show that vector summation with shared covariance is the most reliable overall strategy, whereas simple summation without shared covariance performs poorly. TSVM improves performance in some settings, but its ability to mitigate multilingual interference is limited. We also find that performance is sensitive to both weight scale and rank ratio, with larger-than-default scaling and relatively low rank often yielding better results. These findings clarify the practical strengths and limits of current vector merging methods for MKE and provide guidance for future multilingual knowledge editing research.

Lifelong Model Editing aims to continuously update evolving facts in Large Language Models while preserving unrelated knowledge and general capabilities, yet it remains plagued by catastrophic forgetting and model collapse. Empirically, we find that recent editors resilient over long horizons share the same core strategy: Lifelong Normalization (LN), which normalizes value gradients using running statistics. Removing LN causes immediate performance collapse, and we observe a counter-intuitive positive cumulative effect where early edits can promote the success of future edits. Yet the mechanism of LN remains a "black box", leaving its precise role in lifelong stability poorly understood. In this work, we provide the first theoretical account of LN in the lifelong regime. Our analysis reveals a self-reinforcing stability loop and proves that, when combined with ridge-regularized regression, LN yields parameter updates with asymptotic orthogonality and bounded norms, directly mitigating forgetting and systemic collapse. Based on these insights, we derive StableEdit, which strengthens this stability loop via an explicit warm-up stage and full whitening, improving long-horizon stability at minimal overhead. Extensive experiments validate our theory and demonstrate competitive performance. Our code is available at https://github.com/MINE-USTC/StableEdit.

Agent-compiled knowledge bases provide persistent external knowledge for large language model (LLM) agents in open-ended, knowledge-intensive downstream tasks. Yet their quality is systematically limited by incompleteness, incorrectness, and redundancy, manifested as missing evidence or cross-document links, low-confidence or imprecise claims, and ambiguous or coreference resolution issues. Such defects compound under iterative use, degrading retrieval fidelity and downstream task performance. We present DeepRefine, a general LLM-based reasoning model for agent-compiled knowledge refinement that improves the quality of any pre-constructed knowledge bases with user queries to make it more suitable for the downstream tasks. DeepRefine performs multi-turn interactions with the knowledge base and conducts abductive diagnosis over interaction history, localizes likely defects, and executes targeted refinement actions for incremental knowledge base updates. To optimize refinement policies of DeepRefine without gold references, we introduce a Gain-Beyond-Draft (GBD) reward and train the reasoning process end-to-end via reinforcement learning. Extensive experiments demonstrate consistent downstream gains over strong baselines.

Large language models (LLMs) increasingly rely on knowledge editing to support knowledge-intensive reasoning, but this flexibility also introduces critical safety risks: adversaries can inject malicious or misleading knowledge that corrupts downstream reasoning and leads to harmful outcomes. Existing knowledge editing benchmarks primarily focus on editing efficacy and lack a unified framework for systematically evaluating the safety implications of edited knowledge on reasoning behavior. To address this gap, we present EditRisk-Bench, a benchmark for systematically evaluating safety risks of knowledge-intensive reasoning under malicious knowledge editing. Unlike prior benchmarks that mainly emphasize edit success, generalization, and locality, EditRisk-Bench focuses on how injected knowledge affects downstream reasoning behavior and reliability. It integrates diverse malicious scenarios, including misinformation, bias, and safety violations, together with multi-level knowledge-intensive reasoning tasks and representative editing strategies within a unified evaluation framework measuring attack effectiveness, reasoning correctness, and side effects. Extensive experiments on both open-source and closed-source LLMs show that malicious knowledge editing can reliably induce incorrect or unsafe reasoning while largely preserving general capabilities, making such risks difficult to detect. We further identify several key factors influencing these risks, including edit scale, knowledge characteristics, and reasoning complexity. EditRisk-Bench provides an extensible testbed for understanding and mitigating safety risks in knowledge editing for LLMs.

Null-space-based methods have garnered considerable attention in model editing by constraining updates to the null space of the pre-existing knowledge representation, thereby preserving the model's original behavior. However, in practice these methods rely on an approximate null space--leading to knowledge leakage--and further suffer from severe performance degradation during sequential editing. Recent work shows that history-aware editing strategies can empirically mitigate this decline, yet the underlying reason remains unclear. In this paper, we first expose the knowledge leakage inherent in existing null-space approaches and then analyze why history-aware updates effectively preserve both editing performance and general capabilities during long-horizon editing. Building on these insights, we propose BetaEdit, a refined framework that effectively controls the knowledge leakage and integrates history-aware updates into the null-space paradigm. Extensive experiments on three large language models across two standard benchmarks show that BetaEdit consistently outperforms prior methods in the challenging regime of massive-scale sequential editing. Code is available at: https://github.com/lbq8942/BetaEdit.

Local factual edits in scientific manuscripts often create non-local revision obligations. If a dataset changes from 215 to 80 documents, claims such as 'medium-scale' or 'a few hundred items' may also become stale, even though they do not repeat the edited number. In an audit of recent arXiv cs.CL benchmark and dataset papers, we find fact-dependent qualitative claims in 37.2% of papers, suggesting that this dependency pattern is common in the target genre. We introduce EditPropBench, a benchmark for measuring whether LLM editors propagate factual edits through dependent manuscript claims. Each item contains an ML/NLP-style synthetic manuscript, a targeted edit, and a controlled fact graph with sentence-level labels for direct targets, required downstream updates, and unrelated text that should remain unchanged. We summarize cascade success with Edit-Ripple Adherence (ERA), the fraction of required downstream updates correctly revised, and validate the metric with adversarial probes and stress-test variants. On the hardest cases, where dependent claims use implicit or free-form wording rather than repeating the edited value, five LLM editing systems span ERA 0.148-0.705. Even the strongest misses roughly 30% of required cascade updates. This advantage persists in a mixed evaluation that includes easy cases solvable by deterministic substitution. EditPropBench shows that current LLM editors can repair many implicit consequences of factual edits, but reliable scientific revision still requires cascade-aware checking.

Large language models encode vast factual knowledge that can become outdated or incorrect after deployment, yet retraining is prohibitively costly. This motivates lifelong model editing, which updates targeted behavior while preserving the rest of the model. Existing editors, both parameter-modifying and parameter-preserving, degrade severely as edits accumulate and struggle to generalize across paraphrases. We propose HoReN, a codebook-based parameter-preserving editor that wraps a single MLP layer with a discrete key-value memory. HoReN treats each codebook entry as both a knowledge key and a Hopfield stored pattern, retrieves edits by angular similarity on the unit hypersphere, and refines queries through damped Hopfield dynamics so paraphrases converge to the correct memory basin while unrelated inputs remain stable. HoReN achieves strong editing performance with consistent gains across diverse benchmarks spanning standard ZsRE, structured WikiBigEdit, and unstructured UnKE evaluations. Moreover, HoReN scales to 50K sequential edits on ZsRE with stable overall performance above 0.93, while prior editors collapse or degrade severely before reaching 10K. Our code is available at https://github.com/ha11ucin8/HoReN.

LLM parameter editing methods commonly rely on computing an ideal target hidden-state at a target layer (referred as anchor point) and distributing the target vector to multiple preceding layers (commonly known as backward spreading) for cooperative editing. Although widely used for a long time, its underlying basis have not been systematically investigated. In this paper, we first conduct a systematic study of its foundations, which helps clarify its capability boundaries, practical considerations, and potential failure modes. Then, we propose a simple and elegant alternative that replaces backward spreading with forward-propagation. Instead of optimizing the target at the last editing layer, we optimize the anchor point at the first editing layer, and then propagate it forward to obtain accurate and mutually compatible target hidden-states for all subsequent editing layers. This approach achieves the same computational complexity as existing methods while producing more accurate layer-wise targets. Our method is simple, without interfering with either the computation of the initial target hidden state or any other components of the subsequent editing pipeline, and thus constituting a benefit for a wide range of LLM parameter editing methods.

Large language models (LLMs) require frequent knowledge updates to reflect changing facts and mitigate hallucinations. To meet this demand, lifelong knowledge editing has emerged as a continual approach to modify specific pieces of knowledge without retraining the entire model. Existing parameter editing methods struggle with stability during sequential edits due to catastrophic forgetting. While retrieval-based approaches are proposed to alleviate this issue, their applicability remains limited across various datasets because of high training costs. To address these limitations and enhance scalability in lifelong settings, we propose LightEdit. Our framework first selects relevant knowledge from retrieved information to modify the query effectively. It then incorporates a decoding strategy to suppress the model's original knowledge probabilities, thereby enabling efficient edits based on the selected information. Extensive experiments on ZSRE, Counterfact, and RIPE benchmarks demonstrate that LightEdit outperforms existing lifelong knowledge editing methods. Furthermore, by minimizing training costs, LightEdit achieves cost-effective scalability, enabling easy adaptation to various datasets.

Although Knowledge Editing provides an efficient mechanism for updating the knowledge of Multimodal Large Language Models (MLLMs), we find that current paradigms still suffer from an important yet remain underexplored issue : editing decoupling failure, where entity-related knowledge can be updated when the model is triggered by multimodal inputs (text--image query pairs), however, it often reverts to outdated pre-edit facts when the paired inputs are split into unimodal ones. Our in-depth empirical analysis reveals that the entity knowledge in MLLMs is not stored as a unified representation, but is instead distributed across disentangled modality-specific pathways. As a result, updates biased toward multimodal queries fail to propagate effectively to unimodal circuits. To bridge this gap, we propose DECODE, which explicitly disentangles and localizes modality-specific neuron groups for targeted knowledge. Extensive experiments demonstrate that DECODE consistently achieves effective knowledge updates under different modality triggers, thereby mitigating editing decoupling failures.

Knowledge editing methods such as ROME and MEMIT update factual associations in transformer models by modifying MLP weights. While evaluated mainly by output behavior, their internal mechanism remains underexplored. We investigate whether edits rely on a common mechanism, regardless of which fact is modified. Despite fact-specific weight changes, we argue that ROME and MEMIT target the same subset of weights critical for maintaining edits. To isolate this subset, we train a compact binary mask over the edited weights. The mask reverses 80% of edits on the training set and over 70% on the test set, confirming that diverse edits share a common functional structure. Our analysis reveals that the mask reverses edits by eliminating overattention in later layers. Additionally, we show that injecting the mask during editing drops editing success from 98% to 38%, demonstrating that this mechanism is necessary for edits to succeed. Our finding that edits suppress rather than overwrite knowledge explains why ROME and MEMIT fail to propagate changes to related facts. The identified common functional subspace informs detection and defense against unwanted edits.

Large language models store not only isolated facts but also rules that support reasoning across symbolic expressions, natural language explanations, and concrete instances. Yet most model editing methods are built for fact-level knowledge, assuming that a target edit can be achieved through a localized intervention. This assumption does not hold for rule-level knowledge, where a single rule must remain consistent across multiple interdependent forms. We investigate this problem through a mechanistic study of rule-level knowledge editing. To support this study, we extend the RuleEdit benchmark from 80 to 200 manually verified rules spanning mathematics and physics. Fine-grained causal tracing reveals a form-specific organization of rule knowledge in transformer layers: formulas and descriptions are concentrated in earlier layers, while instances are more associated with middle layers. These results suggest that rule knowledge is not uniformly localized, and therefore cannot be reliably edited by a single-layer or contiguous-block intervention. Based on this insight, we propose Distributed Multi-Layer Editing (DMLE), which applies a shared early-layer update to formulas and descriptions and a separate middle-layer update to instances. While remaining competitive on standard editing metrics, DMLE achieves substantially stronger rule-level editing performance. On average, it improves instance portability and rule understanding by 13.91 and 50.19 percentage points, respectively, over the strongest baseline across GPT-J-6B, Qwen2.5-7B, Qwen2-7B, and LLaMA-3-8B. The code is available at https://github.com/Pepper66/DMLE.

Large Language Models (LLMs) internalize vast world knowledge as parametric memory, yet inevitably inherit the staleness and errors of their source corpora. Consequently, ensuring the reliability and malleability of these internal representations is imperative for trustworthy real-world deployment. Knowledge editing offers a pivotal paradigm for surgically modifying memory without retraining. However, while recent editors demonstrate high success rates on standard benchmarks, it remains questionable whether current evaluation frameworks that rely on assessing output under specific prompting conditions can reliably authenticate genuine memory modification. In this work, we introduce a simple diagnostic framework that subjects models to discriminative self-assessment under in-context learning (ICL) settings that better reflect real-world application environments, specifically designed to scrutinize the subtle behavioral nuances induced by memory modifications. This probing reveals a pervasive phenomenon of Surface Compliance, where editors achieve high benchmark scores by merely mimicking target outputs without structurally overwriting internal beliefs. Moreover, we find that recursive modifications accumulate representational residues, triggering cognitive instability and permanently diminishing the reversibility of the model's memory state. These insights underscore the risks of current editing paradigms and highlight the pivotal role of robust memory modification in building trustworthy, long-term sustainable LLM systems. Code is available at https://github.com/XiaojieGu/SA-MCQ.

Deploying Large Language Models (LLMs) in real-world dynamic environments raises the challenge of updating their pre-trained knowledge. While existing knowledge editing methods can reliably patch isolated facts, they frequently suffer from a reasoning gap, where the model recalls the edited fact but fails to utilize it in multi-step reasoning chains. Our analysis shows that multi-hop reasoning relies on sparse circuitry beyond direct factual recall, with functionally differentiated components contributing to intermediate processing and final-answer prediction. To bridge this gap, we introduce MCircKE (Mechanistic Circuit-based Knowledge Editing), a mechanistically grounded framework that enables a map-and-adapt editing procedure. MCircKE first identifies the causal circuits responsible for a specific reasoning task, capturing both the storage of the fact and the routing of its logical consequences. It then surgically update parameters exclusively within this mapped circuit. Extensive experiments on the MQuAKE-series benchmarks demonstrate the effectiveness of the proposed method for multi-hop reasoning in knowledge editing.

Large language models (LLMs) can effectively handle outdated information through knowledge editing. However, current approaches face two key limitations: (I) Poor generalization: Most approaches rigidly inject new knowledge without ensuring that the model can use it effectively to solve practical problems. (II) Narrow scope: Current methods focus primarily on structured fact triples, overlooking the diverse unstructured forms of factual information (e.g., news, articles) prevalent in real-world contexts. To address these challenges, we propose a new paradigm: teaching LLMs to edit knowledge via Chain of Thoughts (CoTs) reasoning (CoT2Edit). We first leverage language model agents for both structured and unstructured edited data to generate CoTs, building high-quality instruction data. The model is then trained to reason over edited knowledge through supervised fine-tuning (SFT) and Group Relative Policy Optimization (GRPO). At inference time, we integrate Retrieval-Augmented Generation (RAG) to dynamically retrieve relevant edited facts for real-time knowledge editing. Experimental results demonstrate that our method achieves strong generalization across six diverse knowledge editing scenarios with just a single round of training on three open-source language models. The codes are available at https://github.com/FredJDean/CoT2Edit.

While locate-then-edit knowledge editing efficiently updates knowledge encoded within Large Language Models (LLMs), a critical generalization failure mode emerges in the practical same-subject knowledge editing scenario: models fail to recall the updated knowledge when following user instructions, despite successfully recalling it in the original edited form. This paper identifies the geometric root of this generalization collapse as a fundamental conflict where the inner activation drifts induced by prompt variations exceed the model's geometric tolerance for generalization after editing. We attribute this instability to a dual pathology: (1) The joint optimization with orthogonal gradients collapses solutions into sharp minima with narrow stability, and (2) the standard covariance constraint paradoxically acts as a Covariance Trap that amplifies input perturbations. To resolve this, we introduce RoSE (Robust Same-subject Editing), which employs Isotropic Geometric Alignment to minimize representational deviation and Hierarchical Knowledge Integration to smooth the optimization landscape. Extensive experiments demonstrate that RoSE significantly improves instruction-following capabilities, laying the foundation for robust interactive parametric memory of LLM agents.

Large Language Models (LLMs) often suffer from catastrophic forgetting and collapse during sequential knowledge editing. This vulnerability stems from the prevailing dense editing paradigm, which treats models as black boxes and relies on coarse-grained parameter interventions that inevitably disrupt preserved knowledge. To address this, we propose SCAN (a sparse editing framework based on Sparse Circuit Anchored Neuron) which transforms editing into a mechanism-aware manipulation by constructing a knowledge circuit via Sparse Transcoders. Experiments on Gemma2, Qwen3, and Llama3.1 across CounterFact, ZsRE and WikiFactDiff demonstrate that SCAN achieves a superior performance, maintaining model integrity on benchmarks like MMLU and GSM8K even after 3,000 sequential edits, whereas other existing methods deteriorate progressively as editing accumulates, eventually resulting in model collapse.

Existing locate-then-edit Knowledge Editing (KE) methods typically decompose editing into two stages: upstream target representation optimization and downstream constrained parameter optimization. The optimization across the two stages is disconnected: upstream applies uniform regularization without observing downstream realization of the planned residual, hindering a refined accuracy-editability trade-off. Since this realization is request-specific and depends on downstream constraints, uniform regularization can over-shrink high-association requests, causing insufficient editing, while it can under-regularize low-association requests, producing over-large planned residuals that reduce downstream editability. To bridge this disconnect, we propose MetaKE (Meta-learning for Knowledge Editing), a new framework that unifies upstream and downstream stages into a bi-level optimization problem. The inner level optimizes parameter updates for the target representation, while the outer level optimizes representation using feedback from downstream constraints, achieving a better semantic accuracy-editability trade-off. To avoid costly multi-layer backpropagation, we introduce a Structural Gradient Proxy to approximate and propagate this feedback. Extensive experiments show that MetaKE outperforms strong baselines, offering a new perspective on KE.

Knowledge editing in Large Language Models (LLMs) aims to update the model's prediction for a specific query to a desired target while preserving its behavior on all other inputs. This process typically involves two stages: identifying the layer to edit and performing the parameter update. Intuitively, different queries may localize knowledge at different depths of the model, resulting in different sample-wise editing performance for a fixed editing layer. In this work, we hypothesize the existence of fixed golden layers that can achieve near-optimal editing performance similar to sample-wise optimal layers. To validate this hypothesis, we provide empirical evidence by comparing golden layers against ground-truth sample-wise optimal layers. Furthermore, we show that golden layers can be reliably identified using a proxy dataset and generalize effectively to unseen test set queries across datasets. Finally, we propose a novel method, namely Layer Gradient Analysis (LGA) that estimates golden layers efficiently via gradient-attribution, avoiding extensive trial-and-error across multiple editing runs. Extensive experiments on several benchmark datasets demonstrate the effectiveness and robustness of our LGA approach across different LLM types and various knowledge editing methods.

Editing Large language models (LLMs) with real-world, unstructured knowledge is essential for correcting and updating their internal parametric knowledge. In this work, we revisit the fundamental next-token prediction (NTP) as a candidate paradigm for unstructured editing. We identify Context Reliance as a critical failure mode of NTP-based approaches, where knowledge acquired from edited text becomes highly dependent on its preceding context, leading to recall failures when that context is absent during inference. This hypothesis is supported by our empirical validation that prepending context during inference recovers knowledge recall. We further theoretically demonstrate that Context Reliance is an inherent consequence of gradient-based optimization, which tends to bind acquired knowledge to a specific aggregated contextual representation. To address this, we propose a simple yet effective COntext-INdependent editing framework (COIN), encouraging model to focus on knowledge within local scope rather than memorizing contextual patterns. Evaluations show that COIN reduces Context Reliance by 45.2% and outperforms strong baselines by 23.6% in editing success rate, highlighting the vital role of mitigating Context Reliance for robust editing.

Enabling artificial intelligence systems, particularly large language models, to update knowledge and flexibly apply it during reasoning remains a central challenge. Existing knowledge editing approaches emphasize atomic facts, improving factual recall but often failing to integrate updated information into a coherent framework usable across contexts. In this work, we argue that knowledge update is fundamentally a reasoning problem rather than a memorization problem. Consequently, a model should be trained in situations where the new information is instrumental to solving a task, combined with pre-existing knowledge, and exercised through multi-step reasoning. Based on this insight, we propose a training strategy based on three principles. First, new knowledge is introduced as a coherent background story that contextualizes novel facts and explains their relation to existing knowledge. Second, models are trained using self-generated multi-hop questions that require multi-step reasoning involving the new information. Third, training is done using knowledge distillation, forcing a student model to internalize the teacher's reasoning behavior without access to the novel information. Experiments show that models trained with this strategy effectively leverage newly acquired knowledge during reasoning and achieve remarkable performance on challenging questions that require combining multiple new facts.

Large language models (LLMs) often produce incorrect or outdated content after being employed. Efficient and accurate knowledge updates without costly retraining are a major challenge. This problem is particularly challenging in lifelong settings, where complex, unstructured knowledge must coexist without interference. We introduce RILKE (Representation Intervention for Lifelong KnowledgE Control), a robust and scalable method that treats knowledge control as interventions within the model's representation space. Leveraging representation-space expressiveness, we identify two key properties enabling RILKE to achieve fine-grained control over complex, unstructured knowledge while maintaining general utility with frozen base weights. During training, RILKE learns paraphrase-robust and edit-localized modules that limit each update to a low-dimensional subspace to minimize cross-edit interference. At inference, a query-adaptive router selects the appropriate module to guide the model's generation. Across LLaMA and Qwen models, RILKE scales effectively to large-scale benchmarks, demonstrating high edit success and strong paraphrase generalization while preserving general utility with modest memory overhead. These results show RILKE is an effective and scalable solution for lifelong knowledge control in LLMs.

Knowledge editing (KE) offers a lightweight alternative to retraining for updating 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 practical objectives: removing covert or malicious edits, and preserving beneficial edits. If fine-tuning impairs edits (Fig.1), current KE methods become less efficient, as a newly fine-tuned model requires re-editing; 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 across 254 experimental configurations. Our results show that in general, edits decay substantially after subsequent fine-tuning. AlphaEdit exhibits the greatest decay on the zsRE benchmark when applied to GPT-J, where 25.27% of previously successful edits become unsuccessful after fine-tuning. We further find that fine-tuning only the edited layers is sufficient to effectively remove edits, while incurring only modest degradation in downstream performance. Surprisingly, fine-tuning non-edited layers leads to greater edit decay than all-layer fine-tuning. Besides, our activation space analysis reveals that fine-tuning produces a larger and more coherent representational shift, both in magnitude and direction, than KE. Overall, our study underscores the necessity of evaluating KE within the broader LLM application pipeline.

Language models (LMs) increasingly drive real-world applications that require world knowledge. However, the internal processes through which models turn data into representations of knowledge and beliefs about the world are poorly understood. To facilitate such studies, we present LMEnt, a suite including (1) a knowledge-rich pretraining corpus, fully annotated with entity mentions based on Wikipedia, (2) an entity-based retrieval method over pretraining data that outperforms existing tools by as much as 80.4%, and (3) 12 pretrained LMs with up to 1B parameters and 4K intermediate checkpoints, with comparable performance to popular open-source models on knowledge tasks. Together, these resources provide a controlled environment for analyzing connections between entity mentions in pretraining data and downstream performance. We show the utility of LMEnt by studying knowledge acquisition over training, finding that entity co-occurrence and mention forms-which are difficult to study with existing tools-affect learning trends. Moreover, as LMs form stronger associations between entities, their facts are harder to edit in-context, whereas inconsistencies in model predictions over training are indicative of editing success. We release LMEnt to support studies of knowledge in LMs, including knowledge representations, plasticity, editing, attribution, hallucinations, and learning dynamics.