Related papers: MetaKE: Meta-Learning for Knowledge Editing Toward…
By searching for shared inductive biases across tasks, meta-learning promises to accelerate learning on novel tasks, but with the cost of solving a complex bilevel optimization problem. We introduce and rigorously define the trade-off…
Large language models (LLMs) acquire knowledge during pre-training, but over time, this knowledge may become incorrect or outdated, necessitating updates after training. Knowledge editing techniques address this issue without the need for…
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…
Sequential knowledge editing in large language models often causes catastrophic collapse of the model's general abilities, especially for parameter-modifying methods. Existing approaches mitigate this issue through heuristic constraints on…
Knowledge editing enables targeted updates without retraining, but prior work focuses on textual or visual facts, leaving abstract auditory perceptual knowledge underexplored. We introduce SAKE, the first benchmark for editing perceptual…
Knowledge editing aims to adjust the knowledge within large language models (LLMs) to prevent their responses from becoming obsolete or inaccurate. However, existing works on knowledge editing are primarily conducted in a single language,…
Knowledge Editing, which efficiently modifies the knowledge in large language models, has gathered great attention. Current benchmarks primarily use multi-hop question answering to assess and analyze newly injected or updated knowledge.…
Knowledge stored in large language models requires timely updates to reflect the dynamic nature of real-world information. To update the knowledge, most knowledge editing methods focus on the low layers, since recent probes into the…
The challenges in recovering underwater images are the presence of diverse degradation factors and the lack of ground truth images. Although synthetic underwater image pairs can be used to overcome the problem of inadequately observing…
Parameter-Preserving Knowledge Editing (PPKE) enables updating models with new information without retraining or parameter adjustment. Recent PPKE approaches used knowledge graphs (KG) to extend knowledge editing (KE) capabilities to…
Meta-learning, the notion of learning to learn, enables learning systems to quickly and flexibly solve new tasks. This usually involves defining a set of outer-loop meta-parameters that are then used to update a set of inner-loop…
A mainstream type of current self-supervised learning methods pursues a general-purpose representation that can be well transferred to downstream tasks, typically by optimizing on a given pretext task such as instance discrimination. In…
Background: Classifications in meta-research enable researchers to cope with an increasing body of scientific knowledge. They provide a framework for, e.g., distinguishing methods, reports, reproducibility, and evaluation in a knowledge…
Large language models (LLMs) have achieved remarkable performance on various natural language tasks. However, they are trained on static corpora and their knowledge can become outdated quickly in the fast-changing world. This motivates the…
Knowledge augmentation has significantly enhanced the performance of Large Language Models (LLMs) in knowledge-intensive tasks. However, existing methods typically operate on the simplistic premise that model performance equates with…
As machine learning models are increasingly deployed in high-stakes settings, e.g. as decision support systems in various societal sectors or in critical infrastructure, designers and auditors are facing the need to ensure that models…
Recent studies pointed out that knowledge distillation (KD) suffers from two degradation problems, the teacher-student gap and the incompatibility with strong data augmentations, making it not applicable to training state-of-the-art models,…
Large language models (LLMs) acquire vast knowledge from large text corpora, but this information can become outdated or inaccurate. Since retraining is computationally expensive, knowledge editing offers an efficient alternative --…
Knowledge editing (KE) methods offer an efficient way to modify knowledge in large language models. Current KE evaluations typically assess editing success by considering only the edited knowledge without any preceding contexts. In…
Deep neural networks are becoming increasingly pervasive in academia and industry, matching and surpassing human performance on a wide variety of fields and related tasks. However, just as humans, even the largest artificial neural networks…