相关论文: MobiEdit: Resource-efficient Knowledge Editing for…

Regular updates are essential for maintaining up-to-date knowledge in large language models (LLMs). Consequently, various model editing methods have been developed to update specific knowledge within LLMs. However, training-based approaches…

Recent advancements in Large Multimodal Models (LMMs) have shown promise in Autonomous Driving Systems (ADS). However, their direct application to ADS is hindered by challenges such as misunderstanding of traffic knowledge, complex road…

Neural language models (LMs) have been extensively trained on vast corpora to store factual knowledge about various aspects of the world described in texts. Current technologies typically employ knowledge editing methods or specific prompts…

Knowledge editing and machine unlearning are two popular approaches for large language models (LLMs) to stay up-to-date. However, the knowledge updating mechanism of LLMs remains largely unexplored due to insufficient, isolated, and…

Large language models (LLMs) acquire vast knowledge from large text corpora, but this information can become outdated or inaccurate.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) aims to efficiently and precisely modify the behavior of large language models (LLMs) to update specific knowledge without negatively influencing other knowledge. Current research primarily focuses on white-box LLMs…

Large Language Models (LLMs) demonstrate exceptional capabilities in factual question answering, yet they sometimes provide incorrect responses. To address this issue, knowledge editing techniques have emerged as effective methods for…

Recent advancements in large language models (LLMs) have indeed showcased their impressive capabilities. On mobile devices, the wealth of valuable, non-public data generated daily holds great promise for locally fine-tuning personalized…

The factual knowledge acquired during pre-training and stored in the parameters of Language Models (LMs) can be useful in downstream tasks (e.g., question answering or textual inference). However, some facts can be incorrectly induced or…

Deploying Large Language Models (LLMs) on edge devices enhances privacy but faces performance hurdles due to limited resources. We introduce a systematic methodology to evaluate on-device LLMs, balancing capability, efficiency, and resource…

Large language models (LLMs) have demonstrated an impressive ability to generate codes on competitive programming tasks. However, with limited sample numbers, LLMs still suffer from poor accuracy. Inspired by the process of human…

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…

Large language models (LLMs) have revolutionized language processing, delivering outstanding results across multiple applications. However, deploying LLMs on edge devices poses several challenges with respect to memory, energy, and compute…

Model editing aims to correct inaccurate knowledge, update outdated information, and incorporate new data into Large Language Models (LLMs) without the need for retraining. This task poses challenges in lifelong scenarios where edits must…

Fine-tuning large language models (LLMs) with backpropagation\textemdash even for a subset of parameters such as LoRA\textemdash can be much more memory-consuming than inference and is often deemed impractical for resource-constrained…

Large language models (LLMs) encode vast world knowledge but struggle to stay up-to-date, often leading to errors and hallucinations. Knowledge editing offers an efficient alternative to retraining, enabling targeted modifications by…

Keeping large language models factually up-to-date is crucial for deployment, yet costly retraining remains a challenge. Knowledge editing offers a promising alternative, but methods are only tested on small-scale or synthetic edit…

Mainstream backdoor attack methods typically demand substantial tuning data for poisoning, limiting their practicality and potentially degrading the overall performance when applied to Large Language Models (LLMs). To address these issues,…

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…

Personalization of Large Language Models (LLMs) is important in practical applications to accommodate the individual needs of different mobile users. Due to data privacy concerns, LLM personalization often needs to be locally done at the…