Related papers: Understanding the Impact of Sampling Quality in Di…

Efficiently aligning large-scale video diffusion models with human intent requires a scalable and trajectory-aware pathway that bridges the inherent discrepancy between training noise distributions and practical inference trajectories.…

Preference optimization methods such as DPO and KTO are widely used for aligning language models, yet little is understood about what properties of preference data drive downstream reasoning gains. We ask: what aspects of a preference pair…

Neural retrieval models excel in Web search, but their training requires substantial amounts of labeled query-document pairs, which are costly to obtain. With the widespread availability of Web document collections like ClueWeb22, synthetic…

In this paper, we introduce \emph{refined Direct Preference Optimization} (rDPO), a method for improving the behavioral alignment of Large Language Models (LLMs) without the need for human-annotated data. The method involves creating…

In large language model (LLM)-based recommendation systems, direct preference optimization (DPO) effectively aligns recommendations with user preferences, requiring multi-negative objective functions to leverage abundant implicit-feedback…

This paper introduces two novel modifications to the Dynamic sAmpling Policy Optimization (DAPO) algorithm [1], approached from a mixed-policy perspective. Standard policy gradient methods can suffer from instability and sample…

Aligning large language models (LLMs) with human preferences is a critical challenge in AI research. While methods like Reinforcement Learning from Human Feedback (RLHF) and Direct Preference Optimization (DPO) are widely used, they often…

Offline algorithms for Reinforcement Learning from Human Preferences (RLHF), which use only a fixed dataset of sampled responses given an input, and preference feedback among these responses, have gained increasing prominence in the…

Large language models (LLMs) are fine-tuned using human comparison data with Reinforcement Learning from Human Feedback (RLHF) methods to make them better aligned with users' preferences. In contrast to LLMs, human preference learning has…

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 ability to train high-performing reward models with few-shot data is critical for enhancing the efficiency and scalability of Reinforcement Learning from Human Feedback (RLHF). We propose a data augmentation and expansion framework that…

Direct alignment algorithms such as Direct Preference Optimization (DPO) fine-tune models based on preference data, using only supervised learning instead of two-stage reinforcement learning with human feedback (RLHF). We show that DPO…

The alignment of large language models (LLMs) often assumes that using more clean data yields better outcomes, overlooking the match between model capacity and example difficulty. Challenging this, we propose a new principle: Preference…

Direct preference optimization (DPO) has shown success in aligning diffusion models with human preference. Previous approaches typically assume a consistent preference label between final generations and noisy samples at intermediate steps,…

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 rapidly increasing capabilities of large language models (LLMs) raise an urgent need to align AI systems with diverse human preferences to simultaneously enhance their usefulness and safety, despite the often conflicting nature of these…

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…

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…

Text-to-image diffusion models deliver high-quality images, yet aligning them with human preferences remains challenging. We revisit diffusion-based Direct Preference Optimization (DPO) for these models and identify a critical pathology:…

Efficient preference optimization algorithms such as Direct Preference Optimization (DPO) have become a popular approach in aligning large language models (LLMs) with human preferences. These algorithms implicitly treat the LLM as a reward…