Generative Social Choice

• URL: http://arxiv.org/abs/2309.01291v2
• Date: Tue, 28 Nov 2023 18:59:31 GMT
• Title: Generative Social Choice
• Authors: Sara Fish, Paul G\"olz, David C. Parkes, Ariel D. Procaccia, Gili Rusak, Itai Shapira, Manuel W\"uthrich
• Abstract summary: 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.
• Score: 30.23505343152816
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Traditionally, social choice theory has only been applicable to choices among a few predetermined alternatives but not to more complex decisions such as collectively selecting a textual statement. We introduce generative social choice, a framework that combines the mathematical rigor of social choice theory with the capability of large language models to generate text and extrapolate preferences. This framework divides the design of AI-augmented democratic processes into two components: first, proving that the process satisfies rigorous representation guarantees when given access to oracle queries; second, empirically validating that these queries can be approximately implemented using a large language model. We apply this framework to the problem of generating a slate of statements that is representative of opinions expressed as free-form text; specifically, we develop a democratic process with representation guarantees and use this process to represent the opinions of participants in a survey about chatbot personalization. We find that 93 out of 100 participants feel "mostly" or "perfectly" represented by the slate of five statements we extracted.

Related papers

• Representative Social Choice: From Learning Theory to AI Alignment [0.0]
  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 naturally formulated as statistical learning problems. We further formulates for representative social choice, and prove Arrow-like axioms with new tools of generalization analysis.
  arXiv  Detail & Related papers  (2024-10-31T14:07:26Z)
• 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)
• Large language models for crowd decision making based on prompt design strategies using ChatGPT: models, analysis and challenges [8.107295925954475]
  Crowd Decision Making (CDM) is a methodology able to infer opinions and decisions from plain texts. Large Language Models (LLMs) lead us to explore new scenarios of automatically understand written texts. This paper analyzes the use of ChatGPT based on prompt design strategies to assist in CDM processes to extract opinions and make decisions.
  arXiv  Detail & Related papers  (2024-03-22T19:21:44Z)
• 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)
• The Whole Truth and Nothing But the Truth: Faithful and Controllable Dialogue Response Generation with Dataflow Transduction and Constrained Decoding [65.34601470417967]
  We describe a hybrid architecture for dialogue response generation that combines the strengths of neural language modeling and rule-based generation. Our experiments show that this system outperforms both rule-based and learned approaches in human evaluations of fluency, relevance, and truthfulness.
  arXiv  Detail & Related papers  (2022-09-16T09:00:49Z)
• Diverse Representation via Computational Participatory Elections -- Lessons from a Case Study [16.699381591572166]
  We have designed a novel participatory electoral process coined the Representation Pact, implemented with the support of a computational system. That process explicitly enables voters to decide on representation criteria in a first round, and then lets them vote for candidates in a second round. After the two rounds, a counting method is applied, which selects the committee of candidates that maximizes the number of votes received in the second round.
  arXiv  Detail & Related papers  (2022-05-30T19:22:38Z)
• Few-Shot Self-Rationalization with Natural Language Prompts [29.23404535276466]
  Self-rationalization models that predict task labels generate free-text elaborations for their predictions. These models are, however, currently trained with a large amount of human-written free-text explanations for each task. We propose to study a more realistic setting of self-rationalization using few training examples.
  arXiv  Detail & Related papers  (2021-11-16T08:21:40Z)
• Explaining Latent Representations with a Corpus of Examples [72.50996504722293]
  We propose SimplEx: a user-centred method that provides example-based explanations with reference to a freely selected set of examples. SimplEx uses the corpus to improve the user's understanding of the latent space with post-hoc explanations. We show that SimplEx empowers the user by highlighting relevant patterns in the corpus that explain model representations.
  arXiv  Detail & Related papers  (2021-10-28T17:59:06Z)
• Dialogue History Matters! Personalized Response Selectionin Multi-turn Retrieval-based Chatbots [62.295373408415365]
  We propose a personalized hybrid matching network (PHMN) for context-response matching. Our contributions are two-fold: 1) our model extracts personalized wording behaviors from user-specific dialogue history as extra matching information. We evaluate our model on two large datasets with user identification, i.e., personalized dialogue Corpus Ubuntu (P- Ubuntu) and personalized Weibo dataset (P-Weibo)
  arXiv  Detail & Related papers  (2021-03-17T09:42:11Z)
• Knowledgeable Dialogue Reading Comprehension on Key Turns [84.1784903043884]
  Multi-choice machine reading comprehension (MRC) requires models to choose the correct answer from candidate options given a passage and a question. Our research focuses dialogue-based MRC, where the passages are multi-turn dialogues. It suffers from two challenges, the answer selection decision is made without support of latently helpful commonsense, and the multi-turn context may hide considerable irrelevant information.
  arXiv  Detail & Related papers  (2020-04-29T07:04:43Z)
• Bridging the Gap: Providing Post-Hoc Symbolic Explanations for Sequential Decision-Making Problems with Inscrutable Representations [44.016120003139264]
  This paper introduces methods for providing contrastive explanations in terms of user-specified concepts for sequential decision-making settings. We do this by building partial symbolic models of a local approximation of the task that can be leveraged to answer the user queries.
  arXiv  Detail & Related papers  (2020-02-04T01:37:56Z)

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.