Intuitions of Compromise: Utilitarianism vs. Contractualism

• URL: http://arxiv.org/abs/2410.05496v1
• Date: Mon, 7 Oct 2024 21:05:57 GMT
• Title: Intuitions of Compromise: Utilitarianism vs. Contractualism
• Authors: Jared Moore, Yejin Choi, Sydney Levine,
• Abstract summary: We use a paradigm that applies algorithms to aggregating preferences across groups in a social decision-making context. While the dominant approach to value aggregation up to now has been utilitarian, we find that people strongly prefer the aggregations recommended by the contractualist algorithm.
• Score: 42.3322948655612
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: What is the best compromise in a situation where different people value different things? The most commonly accepted method for answering this question -- in fields across the behavioral and social sciences, decision theory, philosophy, and artificial intelligence development -- is simply to add up utilities associated with the different options and pick the solution with the largest sum. This ``utilitarian'' approach seems like the obvious, theory-neutral way of approaching the problem. But there is an important, though often-ignored, alternative: a ``contractualist'' approach, which advocates for an agreement-driven method of deciding. Remarkably, no research has presented empirical evidence directly comparing the intuitive plausibility of these two approaches. In this paper, we systematically explore the proposals suggested by each algorithm (the ``Utilitarian Sum'' and the contractualist ''Nash Product''), using a paradigm that applies those algorithms to aggregating preferences across groups in a social decision-making context. While the dominant approach to value aggregation up to now has been utilitarian, we find that people strongly prefer the aggregations recommended by the contractualist algorithm. Finally, we compare the judgments of large language models (LLMs) to that of our (human) participants, finding important misalignment between model and human preferences.

Related papers

• Sequential Manipulation Against Rank Aggregation: Theory and Algorithm [119.57122943187086]
  We leverage an online attack on the vulnerable data collection process. From the game-theoretic perspective, the confrontation scenario is formulated as a distributionally robust game. The proposed method manipulates the results of rank aggregation methods in a sequential manner.
  arXiv  Detail & Related papers  (2024-07-02T03:31:21Z)
• 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: Towards Equitable Alignment of Large Language Models 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)
• Provable Benefits of Policy Learning from Human Preferences in Contextual Bandit Problems [82.92678837778358]
  preference-based methods have demonstrated substantial success in empirical applications such as InstructGPT. We show how human bias and uncertainty in feedback modelings can affect the theoretical guarantees of these approaches.
  arXiv  Detail & Related papers  (2023-07-24T17:50:24Z)
• From Utilitarian to Rawlsian Designs for Algorithmic Fairness [0.0]
  We present a class of objective functions that interpolates between two (possibly) conflicting notions of the good' We compute optimal solutions and construct the tradeoff between utilitarian and Rawlsian notions of the good' This work suggests that the proper degree of fairness' can be informed by a designer's preferences over the space of induced utilitarian and Rawlsian good'
  arXiv  Detail & Related papers  (2023-02-07T16:28:10Z)
• From Explanation to Recommendation: Ethical Standards for Algorithmic Recourse [0.0]
  We argue that recourse should be viewed as a recommendation problem, not an explanation problem. We illustrate by considering the case of diversity constraints on algorithmic recourse.
  arXiv  Detail & Related papers  (2022-05-30T20:09:42Z)
• Learning to be Fair: A Consequentialist Approach to Equitable Decision-Making [21.152377319502705]
  We present an alternative framework for designing equitable algorithms. In our approach, one first elicits stakeholder preferences over the space of possible decisions. We then optimize over the space of decision policies, making trade-offs in a way that maximizes the elicited utility.
  arXiv  Detail & Related papers  (2021-09-18T00:30:43Z)
• Diversity in Kemeny Rank Aggregation: A Parameterized Approach [3.6603644500568806]
  A recent trend in artificial intelligence, called solution diversity, has focused on the development of notions of optimality. In this work, we investigate the impact of this combination in the field of Kemeny Rank Aggregation. Our main results work both when considering the traditional setting of aggregation over linearly ordered votes, and in the more general setting where votes are partially ordered.
  arXiv  Detail & Related papers  (2021-05-19T21:50:03Z)
• Scalable Personalised Item Ranking through Parametric Density Estimation [53.44830012414444]
  Learning from implicit feedback is challenging because of the difficult nature of the one-class problem. Most conventional methods use a pairwise ranking approach and negative samplers to cope with the one-class problem. We propose a learning-to-rank approach, which achieves convergence speed comparable to the pointwise counterpart.
  arXiv  Detail & Related papers  (2021-05-11T03:38:16Z)
• Preference learning along multiple criteria: A game-theoretic perspective [97.94912276610002]
  We generalize the notion of a von Neumann winner to the multi-criteria setting by taking inspiration from Blackwell's approachability. Our framework allows for non-linear aggregation of preferences across criteria, and generalizes the linearization-based approach from multi-objective optimization. We show that the Blackwell winner of a multi-criteria problem instance can be computed as the solution to a convex optimization problem.
  arXiv  Detail & Related papers  (2021-05-05T03:23:11Z)

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.