paper-with-me

Papers

SWEPO: Simultaneous Weighted Preference Optimization for Group Contrastive Alignment

2024-12-05 · Taneesh Gupta, Rahul Madhavan, Xuchao Zhang, Chetan Bansal, Saravan Rajmohan

We introduce Simultaneous Weighted Preference Optimization (SWEPO), a novel extension of Direct Preference Optimization (DPO) designed to accommodate multiple dynamically chosen positive and negative responses for each query. SWEPO employs a weighted group contrastive loss, assigning weights to responses based on their deviation from the mean reward score. This approach effectively prioritizes responses that are significantly better or worse than the average, enhancing optimization. Our theoretical analysis demonstrates that simultaneously considering multiple preferences reduces alignment bias, resulting in more robust alignment. Additionally, we provide insights into the training dynamics of our loss function and a related function, InfoNCA. Empirical validation on the UltraFeedback dataset establishes SWEPO as state-of-the-art, with superior performance in downstream evaluations using the AlpacaEval dataset.

📄 PDF Abstract BibTeX arXiv:2412.04628

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Beyond Pairwise Preferences: Listwise Reward-Aware Alignment for Diffusion Models

2026-05-26 · Austin Wang, Jiaqi Han, Stefano Ermon, Yisong Yue arxiv

Preference optimization has emerged as an efficient alternative to online reinforcement learning from human feedback (RLHF) for aligning text-to-image diffusion models. However, existing methods largely reduce supervisio…

Text-to-Image GenerationReinforcement LearningImage Editing

APPA: Adaptive Preference Pluralistic Alignment for Fair Federated RLHF of LLMs

2026-04-05 · Mahmoud Srewa, Tianyu Zhao, Salma Elmalaki arxiv

Aligning large language models (LLMs) with diverse human preferences requires pluralistic alignment, where a single model must respect the values of multiple distinct groups simultaneously. In federated reinforcement lea…

Reinforcement Learning

Generative AI Empowered Semantic Feature Multiple Access (SFMA) Over Wireless Networks

2024-12-30 · Jiaxiang Wang, Yinchao Yang, Zhaohui Yang, Chongwen Huang 외

This paper investigates a novel generative artificial intelligence (GAI) empowered multi-user semantic communication system called semantic feature multiple access (SFMA) for video transmission, which comprises a base st…

Semantic CommunicationVideo Frame Interpolation

User Grouping and Resource Allocation in Multiuser MIMO Systems under SWIPT

2024-12-03 · Javier Rubio, Antonio Pascual-Iserte

This paper considers a broadcast multiple-input multiple-output (MIMO) network with multiple users and simultaneous wireless information and power transfer (SWIPT). In this scenario, it is assumed that some users are abl…

Scheduling

No Preference Left Behind: Group Distributional Preference Optimization

2024-12-28 · Binwei Yao, Zefan Cai, Yun-Shiuan Chuang, Shanglin Yang 외

Preferences within a group of people are not uniform but follow a distribution. While existing alignment methods like Direct Preference Optimization (DPO) attempt to steer models to reflect human preferences, they strugg…

DiversityLanguage ModelingLanguage Modelling