arXiv Machine Learning
Who Should We Listen to More? Welfare-Aware Preference Acquisition for Pluralistic Alignment
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Oct 1
Optimal Design for Active Preference Learning with Biased LLM Judges
arXiv:2609.38860v1 Announce Type: cross Abstract: Learning from human preferences is central to large language model (LLM) alignment, but human preference annotation is costly. Active preference lear...
arXiv AI
Oct 21
The Reward Model Selection Crisis in Personalized Alignment
arXiv:2512.23067v3 Announce Type: replace Abstract: Personalized alignment from preference data has focused primarily on improving personal reward model (RM) accuracy, with the implicit assumption th...
arXiv Computation and Language
Sep 1
Low-Resource Preference Adaptation of LLMs via Activation-Based Label Propagation
arXiv:2608.30902v1 Announce Type: new Abstract: Adapting large language models to user-specific preferences is often constrained by the cost of human annotation, making preference optimisation imprac...
arXiv Machine Learning
Jul 31
Personalized RewardBench: Evaluating Reward Models with Human Aligned Personalization
arXiv:2604. 07343v2 Announce Type: replace-cross Abstract: Pluralistic alignment has emerged as a critical frontier in the development of Large Language Models (LLMs), with reward models (RMs) serving as a central mechanism for capturing diverse human values.
arXiv AI
Aug 18
Leveraging Machine Unlearning for Cost-Efficient Preference Alignment
arXiv:2504. 06659v2 Announce Type: replace-cross Abstract: Despite advances in Preference Alignment (PA) for Large Language Models (LLMs), mainstream methods like reinforcement learning with human feedback face notable challenges.
arXiv AI
Jun 2
Margin Adaptive DPO: Leveraging Reward Model for Granular Control in Preference Optimization
arXiv:2510. 05342v2 Announce Type: replace-cross Abstract: Direct Preference Optimization (DPO) has emerged as a simple and effective method for aligning large language models.