Abstract Large Language Models (LLMs), such as ChatGPT and Bard, have revolutionized
natural language understanding and generation. They possess deep language …

Misinformation such as fake news and rumors is a serious threat for information ecosystems
and public trust. The emergence of large language models (LLMs) has great potential to …

Abstract Instruction-tuned Large Language Models (LLMs) have become a ubiquitous
platform for open-ended applications due to their ability to modulate responses based on …

We present Virtual Prompt Injection (VPI) for instruction-tuned Large Language Models
(LLMs). VPI allows an attacker-specified virtual prompt to steer the model behavior under …

Reinforcement Learning with Human Feedback (RLHF) is a methodology designed to align
Large Language Models (LLMs) with human preferences, playing an important role in LLMs …

Large Language Models (LLMs) have become a cornerstone in the field of Natural
Language Processing (NLP), offering transformative capabilities in understanding and …

In the burgeoning field of Large Language Models (LLMs), developing a robust safety
mechanism, colloquially known as" safeguards" or" guardrails", has become imperative to …

Aligning large language models (LLMs) with human is a critical step in effectively utilizing
their pre-trained capabilities across a wide array of language tasks. Current instruction …

Safety backdoor attacks in large language models (LLMs) enable the stealthy triggering of
unsafe behaviors while evading detection during normal interactions. The high …

Large-scale natural language processing models have been developed and integrated into
numerous applications, given the advantage of their remarkable performance. Nonetheless …