The rapid advancement of Large Language Models (LLMs) has driven their expanding
application across various fields. One of the most promising applications is their role as …

Protecting the intellectual property of open-source Large Language Models (LLMs) is very
important, because training LLMs costs extensive computational resources and data …

Post-training is essential for enabling large language models (LLMs) to follow human
instructions. Inspired by the recent success of using LLMs to simulate human society, we …

Reinforcement learning from human feedback (RLHF) has proven effective in enhancing the
instruction-following capabilities of large language models; however, it remains …

Safety concerns of Multimodal large language models (MLLMs) have gradually become an
important problem in various applications. Surprisingly, previous works indicate a counter …

Unlearning methods have the potential to improve the privacy and safety of large language
models (LLMs) by removing sensitive or harmful information post hoc. The LLM unlearning …

Learning from preference feedback is a common practice for aligning large language
models~(LLMs) with human value. Conventionally, preference data is learned and encoded …

The risk of harmful content generated by large language models (LLMs) becomes a critical
concern. This paper presents a systematic study on assessing and improving LLMs' …

With the rapid development of large language models (LLMs) and ever-evolving practical
requirements, finding an efficient and effective alignment method has never been more …

As LLMs become more widely deployed, there is increasing interest in directly optimizing for
feedback from end users (eg thumbs up) in addition to feedback from paid annotators …