This study is an empirical investigation into the semantic vulnerabilities of four popular pre-
trained commercial Large Language Models (LLMs) to ideological manipulation. Using …

Reinforcement learning from human feedback (RLHF) is a technique for training AI systems
to align with human goals. RLHF has emerged as the central method used to finetune state …

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 …

As large language models (LLMs) grow more powerful, concerns around potential harms
like toxicity, unfairness, and hallucination threaten user trust. Ensuring beneficial alignment …

Abstract Language models (LMs) often exhibit undesirable text generation behaviors,
including generating false, toxic, or irrelevant outputs. Reinforcement learning from human …

As natural language becomes the default interface for human-AI interaction, there is a critical
need for LMs to appropriately communicate uncertainties in downstream applications. In this …

In this paper, we introduce the BeaverTails dataset, aimed at fostering research on safety
alignment in large language models (LLMs). This dataset uniquely separates annotations of …

As Large Language Models (LLMs) are deployed with increasing real-world responsibilities,
it is important to be able to specify and constrain the behavior of these systems in a reliable …

With the development of large language models (LLMs), striking a balance between the
performance and safety of AI systems has never been more critical. However, the inherent …

Recent advancements in Large Language Models (LLMs) have garnered wide attention and
led to successful products such as ChatGPT and GPT-4. Their proficiency in adhering to …