Adaptive Preference Aggregation

• URL: http://arxiv.org/abs/2503.10215v1
• Date: Thu, 13 Mar 2025 09:57:41 GMT
• Title: Adaptive Preference Aggregation
• Authors: Benjamin Heymann,
• Abstract summary: Social choice theory provides a framework to aggregate preferences, but was not developed for the multidimensional applications typical of AI.<n>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.
• Score: 1.6317061277457001
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: 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.

Related papers

• A Survey of Direct Preference Optimization [103.59317151002693]
  Large Language Models (LLMs) have demonstrated unprecedented generative capabilities. Their alignment with human values remains critical for ensuring helpful and harmless deployments. Direct Preference Optimization (DPO) has recently gained prominence as a streamlined alternative.
  arXiv  Detail & Related papers  (2025-03-12T08:45:15Z)
• Adaptive Alignment: Dynamic Preference Adjustments via Multi-Objective Reinforcement Learning for Pluralistic AI [4.80825466957272]
  We propose an approach for aligning AI with diverse and shifting user preferences through Multi Objective Reinforcement Learning (MORL) In this paper, we introduce the proposed framework for this approach, outline its anticipated advantages and assumptions, and discuss technical details about the implementation.
  arXiv  Detail & Related papers  (2024-10-31T04:46:52Z)
• Learning Reward and Policy Jointly from Demonstration and Preference Improves Alignment [58.049113055986375]
  We develop a single stage approach named Alignment with Integrated Human Feedback (AIHF) to train reward models and the policy.<n>The proposed approach admits a suite of efficient algorithms, which can easily reduce to, and leverage, popular alignment algorithms.<n>We demonstrate the efficiency of the proposed solutions with extensive experiments involving alignment problems in LLMs and robotic control problems in MuJoCo.
  arXiv  Detail & Related papers  (2024-06-11T01:20:53Z)
• RLHF from Heterogeneous Feedback via Personalization and Preference Aggregation [24.374185140811115]
  Reinforcement learning from human feedback (RLHF) has been an effective technique for aligning AI systems with human values. In this paper, we focus on addressing the issues due to the inherent heterogeneity in human preferences, as well as their potential strategic behavior in providing feedback. We propose two frameworks to address heterogeneous human feedback in principled ways: personalization-based one and aggregation-based one.
  arXiv  Detail & Related papers  (2024-04-30T23:57:23Z)
• MaxMin-RLHF: Alignment with Diverse Human Preferences [101.57443597426374]
  Reinforcement Learning from Human Feedback (RLHF) aligns language models to human preferences by employing a singular reward model derived from preference data. We learn a mixture of preference distributions via an expectation-maximization algorithm to better represent diverse human preferences. Our algorithm achieves an average improvement of more than 16% in win-rates over conventional RLHF algorithms.
  arXiv  Detail & Related papers  (2024-02-14T03:56:27Z)
• Personalized Reinforcement Learning with a Budget of Policies [9.846353643883443]
  Personalization in machine learning (ML) tailors models' decisions to the individual characteristics of users. We propose a novel framework termed represented Markov Decision Processes (r-MDPs) that is designed to balance the need for personalization with the regulatory constraints. In an r-MDP, we cater to a diverse user population, each with unique preferences, through interaction with a small set of representative policies. We develop two deep reinforcement learning algorithms that efficiently solve r-MDPs.
  arXiv  Detail & Related papers  (2024-01-12T11:27:55Z)
• Iterative Preference Learning from Human Feedback: Bridging Theory and Practice for RLHF under KL-Constraint [56.74058752955209]
  This paper studies the alignment process of generative models with Reinforcement Learning from Human Feedback (RLHF) We first identify the primary challenges of existing popular methods like offline PPO and offline DPO as lacking in strategical exploration of the environment. We propose efficient algorithms with finite-sample theoretical guarantees.
  arXiv  Detail & Related papers  (2023-12-18T18:58:42Z)
• Reinforcement Learning from Diverse Human Preferences [68.4294547285359]
  This paper develops a method for crowd-sourcing preference labels and learning from diverse human preferences. The proposed method is tested on a variety of tasks in DMcontrol and Meta-world. It has shown consistent and significant improvements over existing preference-based RL algorithms when learning from diverse feedback.
  arXiv  Detail & Related papers  (2023-01-27T15:18:54Z)
• Socio-cognitive Optimization of Time-delay Control Problems using Evolutionary Metaheuristics [89.24951036534168]
  Metaheuristics are universal optimization algorithms which should be used for solving difficult problems, unsolvable by classic approaches. In this paper we aim at constructing novel socio-cognitive metaheuristic based on castes, and apply several versions of this algorithm to optimization of time-delay system model.
  arXiv  Detail & Related papers  (2022-10-23T22:21:10Z)
• Interactive Evolutionary Multi-Objective Optimization via Learning-to-Rank [8.421614560290609]
  This paper develops a framework for designing preference-based EMO algorithms to find solution(s) of interest (SOI) in an interactive manner. Its core idea is to involve human in the loop of EMO. After every several iterations, the DM is invited to elicit her feedback with regard to a couple of incumbent candidates. By collecting such information, her preference is progressively learned by a learning-to-rank neural network and then applied to guide the baseline EMO algorithm.
  arXiv  Detail & Related papers  (2022-04-06T06:34:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.