Generative Social Choice: The Next Generation

• URL: http://arxiv.org/abs/2505.22939v1
• Date: Wed, 28 May 2025 23:40:24 GMT
• Title: Generative Social Choice: The Next Generation
• Abstract summary: Key task in certain democratic processes is to produce a concise slate of statements that proportionally represents the full spectrum of user opinions.<n>This task is similar to committee elections, but unlike traditional settings, the candidate set comprises all possible statements of varying lengths.
• Score: 31.97126215677833
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: A key task in certain democratic processes is to produce a concise slate of statements that proportionally represents the full spectrum of user opinions. This task is similar to committee elections, but unlike traditional settings, the candidate set comprises all possible statements of varying lengths, and so it can only be accessed through specific queries. Combining social choice and large language models, prior work has approached this challenge through a framework of generative social choice. We extend the framework in two fundamental ways, providing theoretical guarantees even in the face of approximately optimal queries and a budget limit on the overall length of the slate. Using GPT-4o to implement queries, we showcase our approach on datasets related to city improvement measures and drug reviews, demonstrating its effectiveness in generating representative slates from unstructured user opinions.

Related papers

• A Self Consistency Based Reranking for Narrative Question Answering [0.2864713389096699]
  We propose a self-ensemble Self-Consistency-Based reranking framework for narrative question answering.<n>The proposed method generates multiple candidate answers for each story-question pair and selects the final answer based on semantic agreement.<n>We evaluate the proposed approach on the NarrativeQA dataset using multiple models, including FLAN-T5 (Base and Small) and Pegasus-Large.
  arXiv  Detail & Related papers  (2026-06-14T10:52:05Z)
• TopBench: A Benchmark for Implicit Prediction and Reasoning over Tabular Question Answering [80.93487993878836]
  A common class of real-world queries is implicitly predictive, requiring the inference of unobserved answers from historical patterns rather than mere retrieval.<n>These queries introduce two challenges: recognizing latent intent and reliable predictive reasoning over massive tables.<n>We introduce TopBench, a benchmark consisting of 779 samples across four sub-tasks, ranging from single-point prediction to decision making, treatment effect analysis, and complex reasoning.
  arXiv  Detail & Related papers  (2026-04-30T16:22:51Z)
• PALM-Bench: A Comprehensive Benchmark for Personalized Audio-Language Models [21.26163892337167]
  Large Audio-Language Models (LALMs) have demonstrated strong performance in audio understanding and generation.<n>We formalize the task of Personalized LALMs (PALM) for recognizing personal concepts and reasoning within personal context.<n>Our experiments on representative open-source LALMs, show that existing training-free prompting and supervised fine-tuning strategies, while yield improvements, remains limited in modeling personalized knowledge.
  arXiv  Detail & Related papers  (2026-01-07T02:44:38Z)
• Reasoning Planning for Language Models [23.519351730129426]
  We introduce EPIC, an Ensemble Planning with Contrastive learning framework.<n>EPIC learns a shared representation space that captures both model reasoning abilities and query-method compatibility.<n> Experiments on diverse mathematical reasoning tasks show that EPIC consistently selects optimal reasoning methods.
  arXiv  Detail & Related papers  (2025-11-01T11:51:53Z)
• Generating Fair Consensus Statements with Social Choice on Token-Level MDPs [7.5036512760759715]
  We model the task as a multi-objective, token-level Markov Decision Process (MDP)<n> Token-level rewards for each agent are derived from their policy (e.g., a personalized language model)<n>This approach utilizes the finding that such policies implicitly define optimal Q-functions, providing a principled way to quantify rewards at each generation step without a value function.
  arXiv  Detail & Related papers  (2025-10-15T21:23:18Z)
• Customize Multi-modal RAI Guardrails with Precedent-based predictions [55.63757336900865]
  A multi-modal guardrail must effectively filter image content based on user-defined policies.<n>Existing fine-tuning methods typically condition predictions on pre-defined policies.<n>We propose to condition model's judgment on "precedents", which are the reasoning processes of prior data points similar to the given input.
  arXiv  Detail & Related papers  (2025-07-28T03:45:34Z)
• Descriptive History Representations: Learning Representations by Answering Questions [22.802988589711337]
  We introduce Descriptive History Representations (DHRs): sufficient statistics characterized by their capacity to answer relevant questions.<n>DHRs focus on capturing the information necessary to address task-relevant queries, providing a structured way to summarize a history for optimal control.<n>This yields representations that capture the salient historical details and predictive structures needed for effective decision making.
  arXiv  Detail & Related papers  (2025-06-02T18:00:41Z)
• Personalized Top-k Set Queries Over Predicted Scores [21.74740893966611]
  This work studies the applicability of expensive external oracles in answering top-k queries over predicted scores.<n>We propose a generic computational framework that handles arbitrary set-based scoring functions.
  arXiv  Detail & Related papers  (2025-02-18T16:19:08Z)
• ACE: A Generative Cross-Modal Retrieval Framework with Coarse-To-Fine Semantic Modeling [53.97609687516371]
  We propose a pioneering generAtive Cross-modal rEtrieval framework (ACE) for end-to-end cross-modal retrieval. ACE achieves state-of-the-art performance in cross-modal retrieval and outperforms the strong baselines on Recall@1 by 15.27% on average.
  arXiv  Detail & Related papers  (2024-06-25T12:47:04Z)
• A Large-Scale Evaluation of Speech Foundation Models [110.95827399522204]
  We establish the Speech processing Universal PERformance Benchmark (SUPERB) to study the effectiveness of the foundation model paradigm for speech. We propose a unified multi-tasking framework to address speech processing tasks in SUPERB using a frozen foundation model followed by task-specialized, lightweight prediction heads.
  arXiv  Detail & Related papers  (2024-04-15T00:03:16Z)
• Improving Interpersonal Communication by Simulating Audiences with Language Models [20.056253963100463]
  We propose the Explore-Simulate-Simulate (EGS) framework, which takes as input any scenario where an individual is communicating to an audience with a goal they want to achieve. EGS produces a diverse set of advice relevant to the scenario, generates communication candidates conditioned on subsets of the advice, and simulates the reactions from various audiences to determine both the best candidate and advice to use. We show that EGS enhances the effectiveness and outcomes of goal-oriented communication across a variety of situations.
  arXiv  Detail & Related papers  (2023-11-01T17:44:50Z)
• Generative Judge for Evaluating Alignment [84.09815387884753]
  We propose a generative judge with 13B parameters, Auto-J, designed to address these challenges. Our model is trained on user queries and LLM-generated responses under massive real-world scenarios. Experimentally, Auto-J outperforms a series of strong competitors, including both open-source and closed-source models.
  arXiv  Detail & Related papers  (2023-10-09T07:27:15Z)
• Generative Social Choice [31.99162448662916]
  We introduce generative social choice, a design methodology for open-ended democratic processes.<n>We prove that the process representation guarantees when given access to oracle queries.<n>We empirically validate that these queries can be approximately implemented using a large language model.
  arXiv  Detail & Related papers  (2023-09-03T23:47:21Z)
• Interpretable by Design: Learning Predictors by Composing Interpretable Queries [8.054701719767293]
  We argue that machine learning algorithms should be interpretable by design. We minimize the expected number of queries needed for accurate prediction. Experiments on vision and NLP tasks demonstrate the efficacy of our approach.
  arXiv  Detail & Related papers  (2022-07-03T02:40:34Z)
• Text Summarization with Latent Queries [60.468323530248945]
  We introduce LaQSum, the first unified text summarization system that learns Latent Queries from documents for abstractive summarization with any existing query forms. Under a deep generative framework, our system jointly optimize a latent query model and a conditional language model, allowing users to plug-and-play queries of any type at test time. Our system robustly outperforms strong comparison systems across summarization benchmarks with different query types, document settings, and target domains.
  arXiv  Detail & Related papers  (2021-05-31T21:14:58Z)
• Automated Concatenation of Embeddings for Structured Prediction [75.44925576268052]
  We propose Automated Concatenation of Embeddings (ACE) to automate the process of finding better concatenations of embeddings for structured prediction tasks. We follow strategies in reinforcement learning to optimize the parameters of the controller and compute the reward based on the accuracy of a task model.
  arXiv  Detail & Related papers  (2020-10-10T14:03:20Z)

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.