paper-with-me

Papers

Knowledge Gradient for Preference Learning

2026-01-29 · Kaiwen Wu, Jacob R. Gardner arxiv

The knowledge gradient is a popular acquisition function in Bayesian optimization (BO) for optimizing black-box objectives with noisy function evaluations. Many practical settings, however, allow only pairwise comparison queries, yielding a preferential BO problem where direct function evaluations are unavailable. Extending the knowledge gradient to preferential BO is hindered by its computational challenge. At its core, the look-ahead step in the preferential setting requires computing a non-Gaussian posterior, which was previously considered intractable. In this paper, we address this challenge by deriving an exact and analytical knowledge gradient for preferential BO. We show that the exact knowledge gradient performs strongly on a suite of benchmark problems, often outperforming existing acquisition functions. In addition, we also present a case study illustrating the limitation of the knowledge gradient in certain scenarios.

📄 PDF Abstract BibTeX arXiv:2601.22335

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

CATNIP: LLM Unlearning via Calibrated and Tokenized Negative Preference Alignment

2026-02-02 · Zhengbang Yang, Yisheng Zhong, Junyuan Hong, Zhuangdi Zhu arxiv

Pretrained knowledge memorized in LLMs raises critical concerns over safety and privacy, which has motivated LLM Unlearning as a technique for selectively removing the influences of undesirable knowledge. Existing approa…

Preference Score Distillation: Leveraging 2D Rewards to Align Text-to-3D Generation with Human Preference

2026-03-02 · Jiaqi Leng, Shuyuan Tu, Haidong Cao, Sicheng Xie 외 arxiv

Human preference alignment presents a critical yet underexplored challenge for diffusion models in text-to-3D generation. Existing solutions typically require task-specific fine-tuning, posing significant hurdles in data…

3D Generation

BPO: Towards Balanced Preference Optimization between Knowledge Breadth and Depth in Alignment

2024-11-16 · Sizhe Wang, Yongqi Tong, Hengyuan Zhang, Dawei Li 외

Reinforcement Learning with Human Feedback (RLHF) is the key to the success of large language models (LLMs) in recent years. In this work, we first introduce the concepts of knowledge breadth and knowledge depth, which m…

Informativeness

Auto-Rubric as Reward: From Implicit Preferences to Explicit Multimodal Generative Criteria

2026-05-08 · Juanxi Tian, Fengyuan Liu, Jiaming Han, Yilei Jiang 외 arxiv

Aligning multimodal generative models with human preferences demands reward signals that respect the compositional, multi-dimensional structure of human judgment. Prevailing RLHF approaches reduce this structure to scala…

Text-to-Image GenerationImage Editing

Aligning Diffusion Language Models via Unpaired Preference Optimization

2025-10-26 · Vaibhav Jindal, Hejian Sang, Chun-Mao Lai, Yanning Chen 외 arxiv

Diffusion language models (dLLMs) are an emerging alternative to autoregressive (AR) generators, but aligning them to human preferences is challenging because sequence log-likelihoods are intractable and pairwise prefere…