paper-with-me

Papers

Adaptive Alignment: Dynamic Preference Adjustments via Multi-Objective Reinforcement Learning for Pluralistic AI

2024-10-31 · Hadassah Harland, Richard Dazeley, Peter Vamplew, Hashini Senaratne, Bahareh Nakisa, Francisco Cruz

Emerging research in Pluralistic Artificial Intelligence (AI) alignment seeks to address how intelligent systems can be designed and deployed in accordance with diverse human needs and values. We contribute to this pursuit with a dynamic approach for aligning AI with diverse and shifting user preferences through Multi Objective Reinforcement Learning (MORL), via post-learning policy selection adjustment. In this paper, we introduce the proposed framework for this approach, outline its anticipated advantages and assumptions, and discuss technical details about the implementation. We also examine the broader implications of adopting a retroactive alignment approach through the sociotechnical systems perspective.

📄 PDF Abstract BibTeX arXiv:2410.23630

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-Objective Reinforcement Learning

Similar Papers 제목 키워드 기반

Preference-Agile Multi-Objective Optimization for Real-time Vehicle Dispatching

2026-04-12 · Jiahuan Jin, Wenhao Zhao, Rong Qu, Jianfeng Ren 외 arxiv

Multi-objective optimization (MOO) has been widely studied in literature because of its versatility in human-centered decision making in real-life applications. Recently, demand for dynamic MOO is fast-emerging due to to…

Reinforcement LearningDecision Making

VideoDPO: Omni-Preference Alignment for Video Diffusion Generation

2024-12-18 · CVPR 2025 1 · Runtao Liu, HaoYu Wu, Zheng Ziqiang, Chen Wei 외

Recent progress in generative diffusion models has greatly advanced text-to-video generation. While text-to-video models trained on large-scale, diverse datasets can produce varied outputs, these generations often deviat…

Image GenerationText-to-Video GenerationVideo Generation

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

Meta-Aligner: Bidirectional Preference-Policy Optimization for Multi-Objective LLMs Alignment

2026-04-27 · Wenzhe Xu, Biao Liu, Yiyang Sun, Xin Geng 외 arxiv

Multi-Objective Alignment aims to align Large Language Models (LLMs) with diverse and often conflicting human values by optimizing multiple objectives simultaneously. Existing methods predominantly rely on static prefere…

Response Generation

AI Alignment through a Game-theoretic Lens: A Survey

2026-08-28 · Yanan Cai, Zhongrui Zhao, Zhigang Lu, Ickjai Lee 외 arxiv

As large language models and increasingly capable AI agents are deployed in high-risk settings, aligning them with complex human values has become a central challenge. Existing alignment methods, while effective in impro…