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 …

Recent years have witnessed remarkable progress made in large language models (LLMs).
Such advancements, while garnering significant attention, have concurrently elicited various …

Reinforcement Learning from Human Feedback (RLHF) is used to align large language
models to produce helpful and harmless responses. Yet, prior work showed these models …

The rapid advancement of large language models (LLMs) presents both opportunities and
challenges, particularly concerning unintentional generation of harmful and toxic responses …

Language models have shown promise in various tasks but can be affected by undesired
data during training, fine-tuning, or alignment. For example, if some unsafe conversations …

The swift advancement in the scales and capabilities of Large Language Models (LLMs)
positions them as promising tools for a variety of downstream tasks. In addition to the pursuit …

Deployable Large Language Models (LLMs) must conform to the criterion of helpfulness and
harmlessness, thereby achieving consistency between LLMs outputs and human values …

Recent advancements in Large Language Models (LLMs) have heightened concerns about
their potential misalignment with human values. However, evaluating their grasp of these …

The emergent capabilities of Large Language Models (LLMs) have made it crucial to align
their values with those of humans. However, current methodologies typically attempt to …

We introduce Aligner, a novel Parameter-Efficient Fine-Tuning (PEFT) method for aligning
multi-billion-parameter-sized Large Language Models (LLMs). Aligner employs a unique …