Evaluating the factuality of long-form text generated by large language models (LMs) is non-
trivial because (1) generations often contain a mixture of supported and unsupported pieces …

Great successes have been reported using Reinforcement Learning from Human Feedback
(RLHF) to align large language models. Open-source preference datasets and reward …

Many applications of large language models (LLMs), ranging from chatbots to creative
writing, require nuanced subjective judgments that can differ significantly across different …

The increasing capabilities of large language models (LLMs) raise opportunities for artificial
general intelligence but concurrently amplify safety concerns, such as potential misuse of AI …

Low-Rank Adaptation~(LoRA), which updates the dense neural network layers with
pluggable low-rank matrices, is one of the best performed parameter efficient fine-tuning …

The reward model for Reinforcement Learning from Human Feedback (RLHF) has proven
effective in fine-tuning Large Language Models (LLMs). Notably, collecting human feedback …

The dominant paradigm in generative modeling consists of two steps: i) pre-training on a
large-scale but unsafe dataset, ii) aligning the pre-trained model with human values via fine …

Aligning language models with human preferences is crucial for reducing errors and biases
in these models. Alignment techniques, such as reinforcement learning from human …

The swift advancement and widespread availability of foundational Large Language Models
(LLMs), complemented by robust fine-tuning methodologies, have catalyzed their adaptation …

Large language models (LLMs) excel in various capabilities but also pose safety risks such
as generating harmful content and misinformation, even after safety alignment. In this paper …