Related papers: Bi-Factorial Preference Optimization: Balancing Sa…

Reinforcement Learning from Human Feedback (RLHF) has emerged as a pivotal technique for large language model (LLM) alignment. This paper studies the setting of online RLHF and focus on improving sample efficiency. All existing algorithms…

Aligning large language models with human preferences is essential for improving interaction quality and safety by ensuring outputs better reflect human values. A promising strategy involves Reinforcement Learning from Human Feedback…

We introduce Adversarial Policy Optimization (AdvPO), a novel solution to the pervasive issue of reward over-optimization in Reinforcement Learning from Human Feedback (RLHF) for Large Language Models (LLMs). Over-optimization occurs when a…

Reinforcement Learning from Human Feedback (RLHF) is commonly employed to tailor models to human preferences, especially to improve the safety of outputs from large language models (LLMs). Traditionally, this method depends on selecting…

Reinforcement learning from human feedback (RLHF) has emerged as a key technique for aligning the output of large language models (LLMs) with human preferences. To learn the reward function, most existing RLHF algorithms use the…

Large language models (LLMs) often contain misleading content, emphasizing the need to align them with human values to ensure secure AI systems. Reinforcement learning from human feedback (RLHF) has been employed to achieve this alignment.…

Instruction following (IF) is a critical capability for large language models (LLMs). However, handling complex instructions with multiple constraints remains challenging. Previous methods typically select preference pairs based on the…

Reinforcement learning from human feedback (RLHF) has emerged as a powerful technique to make large language models (LLMs) easier to use and more effective. A core piece of the RLHF process is the training and utilization of a model of…

The growing safety concerns surrounding large language models raise an urgent need to align them with diverse human preferences to simultaneously enhance their helpfulness and safety. A promising approach is to enforce safety constraints…

Direct Preference Optimization (DPO) has emerged as a more computationally efficient alternative to Reinforcement Learning from Human Feedback (RLHF) with Proximal Policy Optimization (PPO), eliminating the need for reward models and online…

Safety alignment of large language models remains brittle under domain shift and noisy preference supervision. Most existing robust alignment methods focus on uncertainty in alignment data, while overlooking optimization-induced fragility…

Preference learning is a key technology for aligning language models with human values. Reinforcement Learning from Human Feedback (RLHF) is a model-based algorithm to optimize preference learning, which first fits a reward model for…

Model fusion combines multiple Large Language Models (LLMs) with different strengths into a more powerful, integrated model through lightweight training methods. Existing works on model fusion focus primarily on supervised fine-tuning…

Large Language Models (LLMs) have become pivotal in advancing natural language processing, yet their potential to perpetuate biases poses significant concerns. This paper introduces a new framework employing Direct Preference Optimization…

Alignment, endowing a pre-trained Large language model (LLM) with the ability to follow instructions, is crucial for its real-world applications. Conventional supervised fine-tuning (SFT) methods formalize it as causal language modeling…

Human preference alignment is critical in building powerful and reliable large language models (LLMs). However, current methods either ignore the multi-dimensionality of human preferences (e.g. helpfulness and harmlessness) or struggle with…

Multimodal large language models (MLLMs) are essential for building general-purpose AI assistants; however, they pose increasing safety risks. How can we ensure safety alignment of MLLMs to prevent undesired behaviors? Going further, it is…

Preference-based feedback is important for many applications in machine learning where evaluation of a reward function is not feasible. Notable recent examples arise in preference alignment for large language models, including in…

The widespread application of large language models (LLMs) raises increasing demands on ensuring safety or imposing constraints, such as reducing harmful content and adhering to predefined rules. While there have been several works studying…

Direct Preference Optimization (DPO) simplifies reinforcement learning from human feedback (RLHF) for large language models (LLMs) by directly optimizing human preferences without an explicit reward model. We find that during DPO training,…