Model Editing

Benchmarks archive 2025-07-28

No benchmark for this task in the archive.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

1 dataset whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

1 subtask in the archive's task tree.

Parent tasks archive 2025-07-28

Most implemented papers archive 2025-07-28

30 shown of 107 papers with code (193 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Editing Large Language Models: Problems, Methods, and Opportunities
  22 May 2023 4 repositories listed Syntology ran 1 of 1 samples · 0 unverified
  Our objective is to provide valuable insights into the effectiveness and feasibility of each editing technique, thereby assisting the community in making informed decisions on the selection of the most appropriate…
• Locating and Editing Factual Associations in GPT
  10 Feb 2022 4 repositories listed Syntology ran 4 of 15 samples · 11 unverified
  To test our hypothesis that these computations correspond to factual association recall, we modify feed-forward weights to update specific factual associations using Rank-One Model Editing (ROME).
• pyvene: A Library for Understanding and Improving PyTorch Models via Interventions
  12 Mar 2024 3 repositories listed Syntology ran 1 of 10 samples · 9 unverified
  Interventions on model-internal states are fundamental operations in many areas of AI, including model editing, steering, robustness, and interpretability.
• Sparse Autoencoders Find Highly Interpretable Features in Language Models
  15 Sep 2023 3 repositories listed Syntology ran 4 of 11 samples · 7 unverified · 5 pointer-only (licence)
  One hypothesised cause of polysemanticity is \textit{superposition}, where neural networks represent more features than they have neurons by assigning features to an overcomplete set of directions in activation space,…
• Fast Model Editing at Scale
  21 Oct 2021 3 repositories listed Syntology ran 1 of 1 samples · 0 unverified
  To enable easy post-hoc editing at scale, we propose Model Editor Networks using Gradient Decomposition (MEND), a collection of small auxiliary editing networks that use a single desired input-output pair to make fast,…
• The Mirage of Model Editing: Revisiting Evaluation in the Wild
  16 Feb 2025 2 repositories listed Syntology ran 5 of 8 samples · 3 unverified
  Our analysis provides a fundamental reexamination of both the real-world applicability of existing model editing methods and their evaluation practices, and establishes a rigorous evaluation framework with key insights…
• Neuron-Level Sequential Editing for Large Language Models
  5 Oct 2024 2 repositories listed Syntology ran 7 of 7 samples · 0 unverified · 7 pointer-only (licence)
  This work explores sequential model editing in large language models (LLMs), a critical task that involves modifying internal knowledge within LLMs continuously through multi-round editing, each incorporating updates or…
• AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models
  3 Oct 2024 2 repositories listed Syntology ran 1 of 2 samples · 1 unverified · 1 pointer-only (licence)
  To address this, we introduce AlphaEdit, a novel solution that projects perturbation onto the null space of the preserved knowledge before applying it to the parameters.
• Interpreting Arithmetic Mechanism in Large Language Models through Comparative Neuron Analysis
  21 Sep 2024 2 repositories listed Syntology ran 3 of 3 samples · 0 unverified · 3 pointer-only (licence)
  We find arithmetic ability resides within a limited number of attention heads, with each head specializing in distinct operations.
• Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs
  22 Jul 2024 2 repositories listed Syntology ran 5 of 11 samples · 6 unverified
  For example, the LLM red-teaming literature has produced a wide variety of 'jailbreaking' techniques to elicit harmful text from models that were fine-tuned to be harmless.
• Model Editing as a Robust and Denoised variant of DPO: A Case Study on Toxicity
  22 May 2024 2 repositories listed Syntology ran 7 of 12 samples · 5 unverified
  Furthermore, these tuning-based methods require large-scale preference data for training and are susceptible to noisy preference data.
• A Comprehensive Study of Knowledge Editing for Large Language Models
  2 Jan 2024 2 repositories listed
  In this paper, we first define the knowledge editing problem and then provide a comprehensive review of cutting-edge approaches.
• Editing Implicit Assumptions in Text-to-Image Diffusion Models
  14 Mar 2023 2 repositories listed Syntology ran 0 of 1 samples · 1 unverified · 1 pointer-only (licence)
  Our Text-to-Image Model Editing method, TIME for short, receives a pair of inputs: a "source" under-specified prompt for which the model makes an implicit assumption (e.
• Interpretability, Then What? Editing Machine Learning Models to Reflect Human Knowledge and Values
  30 Jun 2022 2 repositories listed
  Machine learning (ML) interpretability techniques can reveal undesirable patterns in data that models exploit to make predictions--potentially causing harms once deployed.
• Model Editing as a Double-Edged Sword: Steering Agent Ethical Behavior Toward Beneficence or Harm
  25 Jun 2025 1 repository listed
  To efficiently steer the ethical behavior of agents, we frame agent behavior steering as a model editing task, which we term Behavior Editing.
• Mitigating Safety Fallback in Editing-based Backdoor Injection on LLMs
  16 Jun 2025 1 repository listed
  Large language models (LLMs) have shown strong performance across natural language tasks, but remain vulnerable to backdoor attacks.
• Drop Dropout on Single-Epoch Language Model Pretraining
  30 May 2025 1 repository listed
  Originally, dropout was seen as a breakthrough regularization technique that reduced overfitting and improved performance in almost all applications of deep learning by reducing overfitting.
• UniErase: Unlearning Token as a Universal Erasure Primitive for Language Models
  21 May 2025 1 repository listed
  Large language models require iterative updates to address challenges such as knowledge conflicts and outdated information (e.
• LyapLock: Bounded Knowledge Preservation in Sequential Large Language Model Editing
  21 May 2025 1 repository listed
  To tackle this, we model the sequential editing as a constrained stochastic programming.
• UltraEdit: Training-, Subject-, and Memory-Free Lifelong Editing in Large Language Models
  20 May 2025 1 repository listed Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
  Lifelong learning enables large language models (LLMs) to adapt to evolving information by continually updating their internal knowledge.
• Cross-Model Transfer of Task Vectors via Few-Shot Orthogonal Alignment
  17 May 2025 1 repository listed
  To address this challenge, we propose a method based on few-shot orthogonal alignment, which aligns task vectors to the parameter space of a differently pre-trained target model.
• NAMET: Robust Massive Model Editing via Noise-Aware Memory Optimization
  17 May 2025 1 repository listed Syntology ran 3 of 3 samples · 0 unverified
  Model editing techniques are essential for efficiently updating knowledge in large language models (LLMs).
• Efficient Model Editing with Task-Localized Sparse Fine-tuning
  3 Apr 2025 1 repository listed
  However, existing methods rely on network linearization to derive task vectors, leading to computational bottlenecks during training and inference.
• Localized Definitions and Distributed Reasoning: A Proof-of-Concept Mechanistic Interpretability Study via Activation Patching
  3 Apr 2025 1 repository listed
  The stronger clean logit difference for definitional questions further supports this localized representation.
• Leaking LoRa: An Evaluation of Password Leaks and Knowledge Storage in Large Language Models
  29 Mar 2025 1 repository listed
  Lastly, Rank One Model Editing (ROME) is used to remove the password information from the model, resulting in the number of passwords recovered going from 37 to 0.
• BiasEdit: Debiasing Stereotyped Language Models via Model Editing
  11 Mar 2025 1 repository listed
  Previous studies have established that language models manifest stereotyped biases.
• SPEED: Scalable, Precise, and Efficient Concept Erasure for Diffusion Models
  10 Mar 2025 1 repository listed Syntology ran 1 of 3 samples · 2 unverified
  Erasing concepts from large-scale text-to-image (T2I) diffusion models has become increasingly crucial due to the growing concerns over copyright infringement, offensive content, and privacy violations.
• CoME: An Unlearning-based Approach to Conflict-free Model Editing
  20 Feb 2025 1 repository listed
  Large language models (LLMs) often retain outdated or incorrect information from pre-training, which undermines their reliability.
• Injecting Universal Jailbreak Backdoors into LLMs in Minutes
  9 Feb 2025 1 repository listed Syntology ran 3 of 4 samples · 1 unverified · 4 pointer-only (licence)
  Our findings underscore the effectiveness, stealthiness, and explainability of JailbreakEdit, emphasizing the need for more advanced defense mechanisms in LLMs.
• Reinforced Lifelong Editing for Language Models
  9 Feb 2025 1 repository listed
  Large language models (LLMs) acquire information from pre-training corpora, but their stored knowledge can become inaccurate or outdated over time.

Syntology lines on 16 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.