Large Language Models (LLMs) are often aligned using contrastive alignment objectives
and preference pair datasets. The interaction between model, paired data, and objective …

This paper surveys research in the rapidly growing field of enhancing large language
models (LLMs) with reinforcement learning (RL), a technique that enables LLMs to improve …

Aligning AI systems with human preferences typically suffers from the infamous reward
hacking problem, where optimization of an imperfect reward model leads to undesired …

Aligning large language models (LLMs) with human values and intentions is crucial for their
utility, honesty, and safety. Reinforcement learning from human feedback (RLHF) is 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 …

Direct Preference Optimization (DPO) and its variants have become the de facto standards
for aligning large language models (LLMs) with human preferences or specific goals …

Preference Optimization (PO) has proven an effective step for aligning language models to
human-desired behaviors. Current variants, following the offline Direct Preference …