Related papers: Pareto-Optimal Learning from Preferences with Hidd…

Aligning Large Language Models (LLMs) with human feedback is crucial for their development. Existing preference optimization methods such as DPO and KTO, while improved based on Reinforcement Learning from Human Feedback (RLHF), are…

Preference-based reinforcement learning (PbRL) has emerged as a promising approach for learning behaviors from human feedback without predefined reward functions. However, current PbRL methods face a critical challenge in effectively…

Large language models (LLMs) demonstrate impressive performance but lack the flexibility to adapt to human preferences quickly without retraining. In this work, we introduce Test-time Preference Optimization (TPO), a framework that aligns…

Recent empirical results have demonstrated that training large language models (LLMs) with negative-only feedback can match or exceed standard reinforcement learning from human feedback (RLHF). Negative Sample Reinforcement achieves parity…

Aligning human preference and value is an important requirement for contemporary foundation models. State-of-the-art techniques such as Reinforcement Learning from Human Feedback (RLHF) often consist of two stages: 1) supervised fine-tuning…

Reinforcement learning algorithms are fundamental to align large language models with human preferences and to enhance their reasoning capabilities. However, current reinforcement learning algorithms often suffer from training instability…

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,…

Personalized preference alignment for LLMs with diverse human preferences requires evaluation and alignment methods that capture pluralism. Most existing preference alignment datasets are logged under policies that differ substantially from…

Aligning large language models (LLM) with human preference plays a key role in building modern generative models and can be achieved by reinforcement learning from human feedback (RLHF). Despite their superior performance, current RLHF…

In this note, we examine the aggregation of preferences achieved by the Group Policy Optimisation (GRPO) algorithm, a reinforcement learning method used to train advanced artificial intelligence models such as DeepSeek-R1-Zero and…

Direct Preference Optimization (DPO) has emerged as a popular alternative to Reinforcement Learning from Human Feedback (RLHF), offering theoretical equivalence with simpler implementation. We prove this equivalence is conditional rather…

Direct alignment algorithms have proven an effective step for aligning language models to human-desired behaviors. Current variants of the Direct Preference Optimization objective have focused on a strict setting where all tokens are…

For AI systems to be useful to humans, they must understand and act in accordance with our values and preferences. Since specifying preferences is a hard task, inverse reinforcement learning (IRL) aims to develop methods that allow for…

Learning from preference feedback has emerged as an essential step for improving the generation quality and performance of modern language models (LMs). Despite its widespread use, the way preference-based learning is applied varies wildly,…

Aligning large language models (LLMs) with diverse and multifaceted user preferences is a fundamental challenge in personalized AI systems. Existing multi-objective alignment methods either rely on costly training or require pre-trained…

Aligning language models to human expectations, e.g., being helpful and harmless, has become a pressing challenge for large language models. A typical alignment procedure consists of supervised fine-tuning and preference learning. Most…

Learning human preferences in language models remains fundamentally challenging, as reward modeling relies on subtle, subjective comparisons or shades of gray rather than clear-cut labels. This study investigates the limits of current…

Preference optimization (PO) is indispensable for large language models (LLMs), with methods such as direct preference optimization (DPO) and proximal policy optimization (PPO) achieving great success. A common belief is that DPO is…

Recent methods leverage a hypernet to handle the performance-fairness trade-offs in federated learning. This hypernet maps the clients' preferences between model performance and fairness to preference-specifc models on the trade-off curve,…

Multi-Objective Optimization (MOO) is an important problem in real-world applications. However, for a non-trivial problem, no single solution exists that can optimize all the objectives simultaneously. In a typical MOO problem, the goal is…