Related papers: Edit Once, Update Everywhere: A Simple Framework f…

Knowledge editing has emerged as an efficient approach for updating factual knowledge in large language models (LLMs). It typically locates knowledge storage modules and then modifies their parameters. However, most existing methods focus…

Knowledge bases (KBs) contain plenty of structured world and commonsense knowledge. As such, they often complement distributional text-based information and facilitate various downstream tasks. Since their manual construction is resource-…

Large language models (LLMs) have demonstrated remarkable capabilities, but they also pose risks related to the generation of toxic or harmful content. This work introduces Precision Knowledge Editing (PKE), an advanced technique that…

In Machine Translation, Large Language Models (LLMs) have generally underperformed compared to conventional encoder-decoder systems and thus see limited adoption. However, LLMs excel at modeling contextual information, making them a natural…

Expanding Large Language Models~(LLMs) to new languages is a costly endeavor, demanding extensive Continued Pre-Training~(CPT) and data-intensive alignment. While recent data-free merging techniques attempt to bypass alignment by fusing a…

Open-source, multilingual medical large language models (LLMs) have the potential to serve linguistically diverse populations across different regions. Adapting generic LLMs for healthcare often requires continual pretraining, but this…

Knowledge representation has been a central aim of AI since its inception. Symbolic Knowledge Graphs (KGs) and neural Large Language Models (LLMs) can both represent knowledge. KGs provide highly accurate and explicit knowledge…

This paper presents a study on strategies to enhance the translation capabilities of large language models (LLMs) in the context of machine translation (MT) tasks. The paper proposes a novel paradigm consisting of three stages: Secondary…

Recently, large language models (LLMs) have demonstrated impressive results but still suffer from hallucinations. Model editing has been proposed to correct factual inaccuracies in LLMs. A challenging case is sequential model editing (SME),…

Large language models (LLMs) demonstrate remarkable text comprehension and generation capabilities but often lack the ability to utilize up-to-date or domain-specific knowledge not included in their training data. To address this gap, we…

Facilitating cross-lingual transfer in multilingual language models remains a critical challenge. Towards this goal, we propose an embedding-based data augmentation technique called XITE. We start with unlabeled text from a low-resource…

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…

Large Language Models~(LLMs) have demonstrated incredible capabilities in understanding, generating, and manipulating languages. Through human-model interactions, LLMs can automatically understand human-issued instructions and output the…

To achieve equitable performance across languages, large language models (LLMs) must be able to abstract knowledge beyond the language in which it was learnt. However, the current literature lacks reliable ways to measure LLMs' capability…

In a rapidly evolving world where information updates swiftly, knowledge in large language models (LLMs) becomes outdated quickly. Retraining LLMs is not a cost-effective option, making knowledge editing (KE) without modifying parameters…

Knowledge editing (KE) provides a scalable approach for updating factual knowledge in large language models without full retraining. While previous studies have demonstrated effectiveness in general domains and medical QA tasks, little…

Model editing aims to precisely alter the behaviors of large language models (LLMs) in relation to specific knowledge, while leaving unrelated knowledge intact. This approach has proven effective in addressing issues of hallucination and…

Multilingual Large Language Models (LLMs) develop cross-lingual abilities despite being trained on limited parallel data. However, they often struggle to generate responses in the intended language, favoring high-resource languages such as…

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…

Recently, knowledge editing on large language models (LLMs) has received considerable attention. Compared to this, editing Large Vision-Language Models (LVLMs) faces extra challenges from diverse data modalities and complicated model…