相关论文: GeoEdit: Geometric Knowledge Editing for Large Lan…

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…

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…

Current knowledge editing methods for large language models (LLMs) struggle to maintain logical consistency when propagating ripple effects to associated facts. We propose ChainEdit, a framework that synergizes knowledge graph-derived…

The important challenge of keeping knowledge in Large Language Models (LLMs) up-to-date has led to the development of various methods for incorporating new facts. However, existing methods for such knowledge editing still face difficulties…

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…

Large Language Models (LLMs) require frequent updates to correct errors and keep pace with continuously evolving knowledge in a timely and effective manner. Recent research in it model editing has highlighted the challenges in balancing…

Large language Model (LLM) unlearning, i.e., selectively removing information from LLMs, is vital for responsible model deployment. Differently, LLM knowledge editing aims to modify LLM knowledge instead of removing it. Though editing and…

Large Language Models (LLMs) excel in natural language processing by encoding extensive human knowledge, but their utility relies on timely updates as knowledge evolves. Updating LLMs involves two key tasks simultaneously: unlearning to…

Large language models (LLMs) store vast amounts of knowledge, which often requires updates to correct factual errors, incorporate newly acquired information, or adapt model behavior. Model editing methods have emerged as efficient solutions…

Knowledge editing aims to update specific facts in large language models (LLMs) without full retraining. Prior efforts sought to tune the knowledge layers of LLMs, achieving improved performance in controlled, teacher-forced evaluations.…

Knowledge editing techniques for large language models (LLMs) can inject knowledge that is later reproducible verbatim, but they fall short on propagating that knowledge: models cannot answer questions that require reasoning with the…

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-editing updates knowledge of large language models (LLMs) and contributes to the interpretability and application of LLMs. However, knowledge applying is context-consistent: LLMs can recall the same knowledge in different…

Knowledge editing has emerged as an effective approach for updating large language models (LLMs) by modifying their internal knowledge. However, their application to the biomedical domain faces unique challenges due to the long-tailed…

We propose an interactive editing method that allows humans to help deep neural networks (DNNs) learn a latent space more consistent with human knowledge, thereby improving classification accuracy on indistinguishable ambiguous data.…

Large language models (LLMs) exhibit impressive language capabilities but remain vulnerable to malicious prompts and jailbreaking attacks. Existing knowledge editing methods for LLM detoxification face two major challenges. First, they…

Instruction-based text editing is increasingly critical for real-world applications such as code editors (e.g., Cursor), but Large Language Models (LLMs) continue to struggle with this task. Unlike free-form generation, editing requires…

Large language models (LLMs) have demonstrated strong reasoning capabilities in text-based mathematical problem solving; however, when adapted to visual reasoning tasks, particularly geometric problem solving, their performance…

Efficiently editing knowledge stored in large language models (LLMs) enables model updates without large-scale training. One possible solution is Locate-and-Edit (L\&E), allowing simultaneous modifications of a massive number of facts.…

Continual post-training aims to extend large language models (LLMs) with new knowledge, skills, and behaviors, yet it remains unclear when sequential updates enable capability transfer and when they cause catastrophic forgetting. Existing…