Adaptive Preference Aggregation
AI alignment, the challenge of ensuring AI systems act in accordance with human values, has emerged as a critical problem in the development of systems such as foundation models and recommender systems. Still, the current dominant approach, reinforcement learning with human feedback (RLHF) faces known theoretical limitations in aggregating diverse human preferences. Social choice theory provides a framework to aggregate preferences, but was not developed for the multidimensional applications typical of AI. Leveraging insights from a recently published urn process, this work introduces a preference aggregation strategy that adapts to the user's context and that inherits the good properties of the maximal lottery, a Condorcet-consistent solution concept.
Code (0)
등록된 구현이 없습니다.
Tasks
Recommendation SystemsSimilar Papers 제목 키워드 기반
APPA: 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 LearningA Systematic Evaluation of Preference Aggregation in Federated RLHF for Pluralistic Alignment of LLMs
This paper addresses the challenge of aligning large language models (LLMs) with diverse human preferences within federated learning (FL) environments, where standard methods often fail to adequately represent diverse vi…
Federated LearningTLSAN: Time-aware Long- and Short-term Attention Network for Next-item Recommendation
Recently, deep neural networks are widely applied in recommender systems for their effectiveness in capturing/modeling users' preferences. Especially, the attention mechanism in deep learning enables recommender systems …
Recommendation SystemsFedAWA: Adaptive Optimization of Aggregation Weights in Federated Learning Using Client Vectors
Federated Learning (FL) has emerged as a promising framework for distributed machine learning, enabling collaborative model training without sharing local data, thereby preserving privacy and enhancing security. However,…
Federated Learningglobal-optimizationRate-Optimal Rank Aggregation with Private Pairwise Rankings
In various real-world scenarios, such as recommender systems and political surveys, pairwise rankings are commonly collected and utilized for rank aggregation to derive an overall ranking of items. However, preference ra…
Recommendation Systems