Related papers: Implicit Preference Alignment for Human Image Anim…

Post-training of LLMs with RLHF, and subsequently preference optimization algorithms such as DPO, IPO, etc., made a big difference in improving human alignment. However, all such techniques can only work with a single (human) objective. In…

Existing AI alignment approaches assume that preferences are static, which is unrealistic: our preferences change, and may even be influenced by our interactions with AI systems themselves. To clarify the consequences of incorrectly…

AI alignment in the shape of Reinforcement Learning from Human Feedback (RLHF) is increasingly treated as a crucial ingredient for high performance large language models. Proximal Policy Optimization (PPO) has been positioned by recent…

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. However, DPO requires high-quality preference data and suffers from…

Reinforcement Learning from Human Feedback (RLHF) is currently the leading approach for aligning large language models with human preferences. Typically, these models rely on extensive offline preference datasets for training. However,…

Current audio captioning relies on supervised learning with paired audio-caption data, which is costly to curate and may not reflect human preferences in real-world scenarios. To address this, we propose a preference-aligned audio…

Aligning Large Language Model (LLM) responses with human preferences is vital for building safe and controllable AI systems. While preference optimization methods based on Plackett-Luce (PL) and Bradley-Terry (BT) models have shown promise,…

Reinforcement Learning from Human Feedback (RLHF) has become central to aligning large language models with human values, typically by first learning a reward model from preference data which is then used to update the model with…

The recent success in using human preferences to align large language models (LLMs) has significantly improved their performance in various downstream tasks, such as question answering, mathematical reasoning, and code generation. However,…

Large Language Models (LLMs) acquire extensive knowledge and remarkable abilities from extensive text corpora, making them powerful tools for various applications. To make LLMs more usable, aligning them with human preferences is essential.…

Feedback Alignment (FA) methods are biologically inspired local learning rules for training neural networks with reduced communication between layers. While FA has potential applications in distributed and privacy-aware ML, limitations in…

Large Vision-Language Models (LVLMs) have shown promising capabilities in understanding and generating information by integrating both visual and textual data. However, current models are still prone to hallucinations, which degrade the…

Reinforcement Learning from Human Feedback and its variants excel in aligning with human intentions to generate helpful, harmless, and honest responses. However, most of them rely on costly human-annotated pairwise comparisons for…

Direct Preference Optimization (DPO) has emerged as a predominant alignment method for diffusion models, facilitating off-policy training without explicit reward modeling. However, its reliance on large-scale, high-quality human preference…

Text-to-image (T2I) models achieve high-fidelity generation through extensive training on large datasets. However, these models may unintentionally pick up undesirable biases of their training data, such as over-representation of particular…

Recent alignment methods based on Direct Preference Optimization (DPO) reformulate preference learning as supervised optimization over pairwise comparisons, offering improved efficiency and stability over reinforcement learning from human…

Preference alignment in diffusion models has primarily focused on benign human preferences (e.g., aesthetic). In this paper, we propose a novel perspective: framing unrestricted adversarial example generation as a problem of aligning with…

Reinforcement learning from human feedback usually models preferences using a reward function that does not distinguish between people. We argue that this is unlikely to be a good design choice in contexts with high potential for…

Recently, tremendous strides have been made to align the generation of Large Language Models (LLMs) with human values to mitigate toxic or unhelpful content. Leveraging Reinforcement Learning from Human Feedback (RLHF) proves effective and…

Reinforcement Learning from Human Feedback (RLHF) has become central to aligning large language models with human values, typically by first learning a reward model from preference data which is then used to update the model with…