Adaptive Alignment: Dynamic Preference Adjustments via Multi-Objective Reinforcement Learning for Pluralistic AI
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Multi-Objective Reinforcement LearningSimilar Papers 제목 키워드 기반
Preference-Agile Multi-Objective Optimization for Real-time Vehicle Dispatching
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 MakingVideoDPO: Omni-Preference Alignment for Video Diffusion Generation
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 GenerationAPPA: Adaptive Preference Pluralistic Alignment for Fair Federated RLHF of LLMs
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 LearningMeta-Aligner: Bidirectional Preference-Policy Optimization for Multi-Objective LLMs Alignment
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 GenerationAI Alignment through a Game-theoretic Lens: A Survey
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…