相关论文: daDPO: Distribution-Aware DPO for Distilling Conve…

Direct Preference Optimization (DPO) is a widely adopted offline algorithm for preference-based reinforcement learning from human feedback (RLHF), designed to improve training simplicity and stability by redefining reward functions.…

A critical component of the current generation of language models is preference alignment, which aims to precisely control the model's behavior to meet human needs and values. The most notable among such methods is Reinforcement Learning…

Learning from human preference is a paradigm used in large-scale language model (LLM) fine-tuning step to better align pretrained LLM to human preference for downstream task. In the past it uses reinforcement learning from human feedback…

Knowledge Distillation (KD) is increasingly adopted to transfer capabilities from large language models to smaller ones, offering significant improvements in efficiency and utility while often surpassing standard fine-tuning. Beyond…

Improving the reasoning capabilities of diffusion-based large language models (dLLMs) through reinforcement learning (RL) remains an open problem. The intractability of dLLMs likelihood function necessitates approximating the current, old,…

Recent advancements in text-to-speech (TTS) have shown that language model (LM)-based systems offer competitive performance to their counterparts. Further optimization can be achieved through preference alignment algorithms, which adjust…

Direct Preference Optimization (DPO) has shown strong potential for mitigating hallucinations in Multimodal Large Language Models (MLLMs). However, existing multimodal DPO approaches often suffer from overfitting due to the difficulty…

Mathematical reasoning presents a significant challenge for Large Language Models (LLMs) as it requires ensuring the correctness of each reasoning step. Researchers have been strengthening the mathematical reasoning abilities of LLMs…

Diffusion Models have revolutionized the field of human motion generation by offering exceptional generation quality and fine-grained controllability through natural language conditioning. Their inherent stochasticity, that is the ability…

Offline preference optimization methods, such as Direct Preference Optimization (DPO), offer significant advantages in aligning Large Language Models (LLMs) with human values. However, achieving optimal performance with these methods…

Recent developments in Direct Preference Optimization (DPO) allow large language models (LLMs) to function as implicit ranking models by maximizing the margin between preferred and non-preferred responses. In practice, user feedback on such…

Knowledge distillation (KD) has shown very promising capabilities in transferring learning representations from large models (teachers) to small models (students). However, as the capacity gap between students and teachers becomes larger,…

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…

Recently, there has been significant interest in replacing the reward model in Reinforcement Learning with Human Feedback (RLHF) methods for Large Language Models (LLMs), such as Direct Preference Optimization (DPO) and its variants. These…

Preferences within a group of people are not uniform but follow a distribution. While existing alignment methods like Direct Preference Optimization (DPO) attempt to steer models to reflect human preferences, they struggle to capture the…

Knowledge distillation offers a transformative pathway to developing powerful, yet efficient, small language models (SLMs) suitable for resource-constrained environments. In this paper, we benchmark the performance and computational cost of…

Recent advancements in Direct Preference Optimization (DPO) have significantly enhanced the alignment of Large Language Models (LLMs) with human preferences, owing to its simplicity and effectiveness. However, existing methods typically…

While Masked Diffusion Models (MDMs), such as LLaDA, present a promising paradigm for language modeling, there has been relatively little effort in aligning these models with human preferences via reinforcement learning. The challenge…

Fairness in Continual Learning for Large Multimodal Models (LMMs) is an emerging yet underexplored challenge, particularly in the presence of imbalanced data distributions that can lead to biased model updates and suboptimal performance…

Diffusion Probabilistic Models (DPMs) have emerged as a powerful class of deep generative models, achieving remarkable performance in image synthesis tasks. However, these models face challenges in terms of widespread adoption due to their…