Language is essentially a complex, intricate system of human expressions governed by
grammatical rules. It poses a significant challenge to develop capable AI algorithms for …

Practitioners commonly align large language models using pairwise preferences, ie, given
labels of the type response A is preferred to response B for a given input. Perhaps less …

This paper studies the theoretical framework of the alignment process of generative models
with Reinforcement Learning from Human Feedback (RLHF). We consider a standard …

Direct Preference Optimization (DPO), which derives reward signals directly from pairwise
preference data, has shown its effectiveness on aligning Large Language Models (LLMs) …

In the era of big data and Artificial Intelligence, an emerging paradigm is to utilize contrastive
self-supervised learning to model large-scale heterogeneous data. Many existing foundation …

Although large language models (LLMs) acquire extensive world knowledge and some
reasoning abilities, their proficiency in generating humorous sentences remains a …

Aligning large language models (LLMs) to human preferences is a crucial step in building
helpful and safe AI tools, which usually involve training on supervised datasets. Popular …

Advancements in large language models (LLMs) have demonstrated remarkable
capabilities across a diverse range of applications. These models excel in generating text …