Large Language Model
Safe LoRA: the Silver Lining of Reducing Safety Risks when Fine-tuning Large Language Models
However, fine-tuning all parameters of LLMs requires significant hardware resources, which can be impractical for typical users.
LLM-AutoDA: Large Language Model-Driven Automatic Data Augmentation for Long-tailed Problems
The long-tailed distribution is the underlying nature of real-world data, and it presents unprecedented challenges for training deep learning models.
ReST-MCTS: LLM Self-Training via Process Reward Guided Tree Search Dan Zhang
Recent methodologies in LLM self-training mostly rely on LLM generating responses and filtering those with correct output answers as training data. This approach often yields a low-quality fine-tuning training set (e.g., incorrect plans or intermediate reasoning).
Supplementary Material for CableInspect AD An Expert Annotated Anomaly Detection
For more information, please refer to the Distribution and Maintenance subsections of the datasheet provided in J. The annotations are in the COCO format. We provide detailed explanations on how the dataset can be read in the code repository.
Fight Back Against Jailbreaking via Prompt Adversarial Tuning Yichuan Mo1Y uji Wang 2 Zeming Wei 3 Yisen Wang 1,4 1
While Large Language Models (LLMs) have achieved tremendous success in various applications, they are also susceptible to jailbreaking attacks.
