Large Language Model
MALL T
Among all the contributing factors, the quality and selection of data is becoming increasingly recognized for its importance in training LLMs effectively.
Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models
In this paper, we introduce a new type of model backdoor: the privacy backdoor attack .
Improving Alignment and Robustness with Circuit Breakers
AI systems can take harmful actions and are highly vulnerable to adversarial attacks.
Fast Attention Over Long Sequences With Dynamic Sparse Flash Attention
Transformer-based language models have found many diverse applications requiring them to process sequences of increasing length.
Theoretical Investigations and Practical Enhancements on Tail Task Risk Minimization in Meta Learning Yiqin Lv Qi Wang
Accordingly, extensive evaluations demonstrate the significance of our proposal and its scalability to multimodal large models in boosting robustness.
AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents
AI agents aim to solve complex tasks by combining text-based reasoning with external tool calls.
Appendix
We provide more information on AIPS' deductive engine and the training process for the value network. To highlight the reasoning ability and maintain readability of proofs, we avoid using brute-force methods such as augmentation-substitution and Wu's method Wu [1978].
comprehensive benchmark on eight tasks
Large Language Models (LLMs) with strong abilities in natural language processing tasks have emerged and have been applied in various kinds of areas such as science, finance and software engineering.