Representative Social Choice: From Learning Theory to AI Alignment

• URL: http://arxiv.org/abs/2410.23953v4
• Date: Thu, 30 Oct 2025 23:39:44 GMT
• Title: Representative Social Choice: From Learning Theory to AI Alignment
• Authors: Tianyi Qiu,
• Abstract summary: In representative social choice, the population is represented by a finite sample of individual-issue pairs.<n>We show that many of the deepest questions in representative social choice can be formulated as statistical learning problems.<n>We formulate further axioms for representative social choice, and prove Arrow-like impossibility theorems with new tools of analysis.
• Score: 1.5831647807014813
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Social choice theory is the study of preference aggregation across a population, used both in mechanism design for human agents and in the democratic alignment of language models. In this study, we propose the representative social choice framework for the modeling of democratic representation in collective decisions, where the number of issues and individuals are too large for mechanisms to consider all preferences directly. These scenarios are widespread in real-world decision-making processes, such as jury trials, legislation, corporate governance, and, more recently, language model alignment. In representative social choice, the population is represented by a finite sample of individual-issue pairs based on which social choice decisions are made. We show that many of the deepest questions in representative social choice can be formulated as statistical learning problems, and prove the generalization properties of social choice mechanisms using the theory of machine learning. We further formulate axioms for representative social choice, and prove Arrow-like impossibility theorems with new combinatorial tools of analysis. Our framework introduces the representative approach to social choice, opening up research directions at the intersection of social choice, learning theory, and AI alignment.

Related papers

• Algorithmic Approaches to Opinion Selection for Online Deliberation: A Comparative Study [1.5267938856942276]
  In online deliberation platforms, algorithmic selection is increasingly used to automate the selection process.<n>It remains unclear how each approach influences desired democratic criteria such as proportional representation.<n>We propose a novel algorithm that incorporates both diversity and a balanced notion of representation in the selection strategy.
  arXiv  Detail & Related papers  (2026-02-17T09:03:26Z)
• Methods and Open Problems in Differentiable Social Choice: Learning Mechanisms, Decisions, and Alignment [7.764532811300023]
  Social choice is no longer a peripheral concern of political theory or economics.<n>This Review surveys differentiable social choice: an emerging paradigm that formulates voting rules, mechanisms, and aggregation procedures as learnable, differentiable models optimized from data.
  arXiv  Detail & Related papers  (2026-02-03T02:17:16Z)
• SocialNLI: A Dialogue-Centric Social Inference Dataset [49.60157928163403]
  We introduce SocialNLI -- the first social dialogue inference dataset.<n>SocialNLI consists of a collection of dialogue transcripts hand-picked to center complex social nuances.<n>We evaluate reasoning models theory-of-mind ability through multi-step counterfactual reasoning.
  arXiv  Detail & Related papers  (2025-10-06T23:42:01Z)
• The Emergence of Altruism in Large-Language-Model Agents Society [7.139078894406603]
  Leveraging Large Language Models for social simulation is a frontier in computational social science.<n>We identify two distinct archetypes: "Adaptive Egoists", which default to prioritizing self-interest but whose altruistic behaviors increase under the influence of a social norm-setting message board.<n>We propose that for social simulation, model selection is not merely a matter of choosing reasoning capability, but of choosing intrinsic social action logic.
  arXiv  Detail & Related papers  (2025-09-26T16:17:29Z)
• LLM-based Agentic Reasoning Frameworks: A Survey from Methods to Scenarios [63.08653028889316]
  We propose a systematic taxonomy that decomposes agentic reasoning frameworks and analyze how these frameworks dominate framework-level reasoning.<n>Specifically, we propose an unified formal language to further classify agentic reasoning systems into single-agent methods, tool-based methods, and multi-agent methods.<n>We provide a comprehensive review of their key application scenarios in scientific discovery, healthcare, software engineering, social simulation, and economics.
  arXiv  Detail & Related papers  (2025-08-25T06:01:16Z)
• Social Genome: Grounded Social Reasoning Abilities of Multimodal Models [61.88413918026431]
  Social reasoning abilities are crucial for AI systems to interpret and respond to multimodal human communication and interaction within social contexts.<n>We introduce SOCIAL GENOME, the first benchmark for fine-grained, grounded social reasoning abilities of multimodal models.
  arXiv  Detail & Related papers  (2025-02-21T00:05:40Z)
• Language Agents as Digital Representatives in Collective Decision-Making [22.656601943922066]
  "representation" is the activity of making an individual's preferences present in the process via participation by a proxy agent.<n>We investigate the possibility of training textitlanguage agents to behave in the capacity of representatives of human agents.
  arXiv  Detail & Related papers  (2025-02-13T14:35:40Z)
• Emergent social conventions and collective bias in LLM populations [0.0]
  Social conventions are the backbone of social coordination, shaping how individuals form a group.<n>We present experimental results that demonstrate the spontaneous emergence of universally adopted social conventions in decentralized populations of large language model (LLM) agents.<n>We then show how strong collective biases can emerge during this process, even when agents exhibit no bias individually.
  arXiv  Detail & Related papers  (2024-10-11T16:16:38Z)
• From Experts to the Public: Governing Multimodal Language Models in Politically Sensitive Video Analysis [48.14390493099495]
  This paper examines the governance of large language models (MM-LLMs) through individual and collective deliberation. We conducted a two-step study: first, interviews with 10 journalists established a baseline understanding of expert video interpretation; second, 114 individuals from the general public engaged in deliberation using Inclusive.AI.
  arXiv  Detail & Related papers  (2024-09-15T03:17:38Z)
• Representation Bias in Political Sample Simulations with Large Language Models [54.48283690603358]
  This study seeks to identify and quantify biases in simulating political samples with Large Language Models. Using the GPT-3.5-Turbo model, we leverage data from the American National Election Studies, German Longitudinal Election Study, Zuobiao dataset, and China Family Panel Studies.
  arXiv  Detail & Related papers  (2024-07-16T05:52:26Z)
• A Theory of LLM Sampling: Part Descriptive and Part Prescriptive [53.08398658452411]
  Large Language Models (LLMs) are increasingly utilized in autonomous decision-making. We show that this sampling behavior resembles that of human decision-making. We show that this deviation of a sample from the statistical norm towards a prescriptive component consistently appears in concepts across diverse real-world domains.
  arXiv  Detail & Related papers  (2024-02-16T18:28:43Z)
• Generative Social Choice [30.23505343152816]
  We introduce generative social choice, a framework that combines the rigor of social choice theory with the capability of large language models to generate text and extrapolate preferences. We apply this framework to the problem of generating a slate of statements that is representative of opinions expressed as free-form text. We find that 93 out of 100 participants feel "mostly" or "perfectly" represented by the slate of five statements we extracted.
  arXiv  Detail & Related papers  (2023-09-03T23:47:21Z)
• Causal Fairness Analysis [68.12191782657437]
  We introduce a framework for understanding, modeling, and possibly solving issues of fairness in decision-making settings. The main insight of our approach will be to link the quantification of the disparities present on the observed data with the underlying, and often unobserved, collection of causal mechanisms. Our effort culminates in the Fairness Map, which is the first systematic attempt to organize and explain the relationship between different criteria found in the literature.
  arXiv  Detail & Related papers  (2022-07-23T01:06:34Z)
• Graph-Based Methods for Discrete Choice [27.874979682322376]
  We use graph learning to study choice in networked contexts. We show that incorporating social network structure can improve the predictions of the standard econometric choice model.
  arXiv  Detail & Related papers  (2022-05-23T14:51:23Z)
• Socially-Optimal Mechanism Design for Incentivized Online Learning [32.55657244414989]
  Multi-arm bandit (MAB) is a classic online learning framework that studies the sequential decision-making in an uncertain environment. It is a practically important scenario in many applications such as spectrum sharing, crowdsensing, and edge computing. This paper establishes the incentivized online learning (IOL) framework for this scenario.
  arXiv  Detail & Related papers  (2021-12-29T00:21:40Z)
• Randomized Classifiers vs Human Decision-Makers: Trustworthy AI May Have to Act Randomly and Society Seems to Accept This [0.8889304968879161]
  We feel that akin to human decisions, judgments of artificial agents should necessarily be grounded in some moral principles. Yet a decision-maker can only make truly ethical (based on any ethical theory) and fair (according to any notion of fairness) decisions if full information on all the relevant factors on which the decision is based are available at the time of decision-making.
  arXiv  Detail & Related papers  (2021-11-15T05:39:02Z)
• Towards Socially Intelligent Agents with Mental State Transition and Human Utility [97.01430011496576]
  We propose to incorporate a mental state and utility model into dialogue agents. The hybrid mental state extracts information from both the dialogue and event observations. The utility model is a ranking model that learns human preferences from a crowd-sourced social commonsense dataset.
  arXiv  Detail & Related papers  (2021-03-12T00:06:51Z)
• Indecision Modeling [50.00689136829134]
  It is important that AI systems act in ways which align with human values. People are often indecisive, and especially so when their decision has moral implications.
  arXiv  Detail & Related papers  (2020-12-15T18:32:37Z)
• Social Choice with Changing Preferences: Representation Theorems and Long-Run Policies [0.0]
  We show how representation theorems from social choice theory can be adapted to characterize optimal policies. We provide an axiomatic characterization of MDP reward functions that agree with the Utilitarianism social welfare functionals of social choice theory.
  arXiv  Detail & Related papers  (2020-11-04T21:21:04Z)
• Decentralized Reinforcement Learning: Global Decision-Making via Local Economic Transactions [80.49176924360499]
  We establish a framework for directing a society of simple, specialized, self-interested agents to solve sequential decision problems. We derive a class of decentralized reinforcement learning algorithms. We demonstrate the potential advantages of a society's inherent modular structure for more efficient transfer learning.
  arXiv  Detail & Related papers  (2020-07-05T16:41:09Z)

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.