Image de couverture de livre

HPS: Hard Preference Sampling for Human Preference Alignment

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zou, Xiandong, Lin, Wanyu, Li, Yuchen, Zhou, Pan
Format:	Preprint
Publié:	2025
Sujets:	Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Preference Ranking Optimization for Human Alignment
par: Song, Feifan, et autres
Publié: (2023)

Disentangling Preference Representation and Text Generation for Efficient Individual Preference Alignment
par: Zhang, Jianfei, et autres
Publié: (2024)

InterMT: Multi-Turn Interleaved Preference Alignment with Human Feedback
par: Chen, Boyuan, et autres
Publié: (2025)

Implicit Safety Alignment from Crowd Preferences
par: Lin, Qian, et autres
Publié: (2026)

ActiveDPO: Active Direct Preference Optimization for Sample-Efficient Alignment
par: Lin, Xiaoqiang, et autres
Publié: (2025)

Strong Preferences Affect the Robustness of Preference Models and Value Alignment
par: Xu, Ziwei, et autres
Publié: (2024)

Note on Martingale Theory and Applications
par: Zou, Xiandong
Publié: (2026)

IBNorm: Information-Bottleneck Inspired Normalization for Representation Learning
par: Zou, Xiandong, et autres
Publié: (2025)

Beyond Preferences in AI Alignment
par: Zhi-Xuan, Tan, et autres
Publié: (2024)

Implicit Preference Alignment for Human Image Animation
par: Wang, Yuanzhi, et autres
Publié: (2026)

Unified Preference Optimization: Language Model Alignment Beyond the Preference Frontier
par: Badrinath, Anirudhan, et autres
Publié: (2024)

Sample Efficient Preference Alignment in LLMs via Active Exploration
par: Mehta, Viraj, et autres
Publié: (2023)

Dissecting Human and LLM Preferences
par: Li, Junlong, et autres
Publié: (2024)

Beyond Ordinal Preferences: Why Alignment Needs Cardinal Human Feedback
par: Whitfill, Parker, et autres
Publié: (2025)

Not All Preferences Are Created Equal: Stability-Aware and Gradient-Efficient Alignment for Reasoning Models
par: Wu, Hui, et autres
Publié: (2026)

From Demonstrations to Rewards: Alignment Without Explicit Human Preferences
par: Zeng, Siliang, et autres
Publié: (2025)

Uncovering Factor Level Preferences to Improve Human-Model Alignment
par: Oh, Juhyun, et autres
Publié: (2024)

Beyond One-Preference-Fits-All Alignment: Multi-Objective Direct Preference Optimization
par: Zhou, Zhanhui, et autres
Publié: (2023)

Preference as Reward, Maximum Preference Optimization with Importance Sampling
par: Jiang, Zaifan, et autres
Publié: (2023)

Direct Alignment with Heterogeneous Preferences
par: Shirali, Ali, et autres
Publié: (2025)

Latent Embedding Adaptation for Human Preference Alignment in Diffusion Planners
par: Ng, Wen Zheng Terence, et autres
Publié: (2025)

PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference
par: Ji, Jiaming, et autres
Publié: (2024)

MaxMin-RLHF: Alignment with Diverse Human Preferences
par: Chakraborty, Souradip, et autres
Publié: (2024)

Human Alignment of Large Language Models through Online Preference Optimisation
par: Calandriello, Daniele, et autres
Publié: (2024)

Capturing Nuanced Preferences: Preference-Aligned Distillation for Small Language Models
par: Gu, Yanggan, et autres
Publié: (2025)

On Diversified Preferences of Large Language Model Alignment
par: Zeng, Dun, et autres
Publié: (2023)

When Can Proxies Improve the Sample Complexity of Preference Learning?
par: Zhu, Yuchen, et autres
Publié: (2024)

Adaptive Helpfulness-Harmlessness Alignment with Preference Vectors
par: Liang, Ren-Wei, et autres
Publié: (2025)

Word Alignment as Preference for Machine Translation
par: Wu, Qiyu, et autres
Publié: (2024)

Retrieval-Feedback-Driven Distillation and Preference Alignment for Efficient LLM-based Query Expansion
par: Li, Minghan, et autres
Publié: (2026)

Putting HUMANS first: Efficient LAM Evaluation with Human Preference Alignment
par: Gan, Woody Haosheng, et autres
Publié: (2026)

LRHP: Learning Representations for Human Preferences via Preference Pairs
par: Wang, Chenglong, et autres
Publié: (2024)

PIPA: Preference Alignment as Prior-Informed Statistical Estimation
par: Li, Junbo, et autres
Publié: (2025)

Human Preferences for Constructive Interactions in Language Model Alignment
par: Kyrychenko, Yara, et autres
Publié: (2025)

Adversarial Preference Learning for Robust LLM Alignment
par: Wang, Yuanfu, et autres
Publié: (2025)

Spread Preference Annotation: Direct Preference Judgment for Efficient LLM Alignment
par: Kim, Dongyoung, et autres
Publié: (2024)

Chain-of-Thought as a Lens: Evaluating Structured Reasoning Alignment between Human Preferences and Large Language Models
par: Wang, Boxuan, et autres
Publié: (2025)

Arithmetic Control of LLMs for Diverse User Preferences: Directional Preference Alignment with Multi-Objective Rewards
par: Wang, Haoxiang, et autres
Publié: (2024)

ProteinOPD: Towards Effective and Efficient Preference Alignment for Protein Design
par: Zhang, Yulin, et autres
Publié: (2026)

ComPO: Preference Alignment via Comparison Oracles
par: Chen, Peter, et autres
Publié: (2025)