Evaluation of Alternative-Based Information Systems for Deliberative Polling using an Agentic Simulator

2026-06-10

AI Summary

This work addresses the challenge of achieving comprehensive coverage of representative arguments in large-scale deliberative voting, particularly in the presence of strategic or adversarial voters. The authors propose an Agent-Based Argumentation Simulator (ABAS) grounded in large language models. They formalize deliberative voting for the first time as a six-tuple encompassing pro/con arguments, attack/support relations, and associated weights. To counter label-flooding attacks, the framework incorporates a reason-recommendation mechanism based on observable support levels and an anti-PageRank relation-weighting strategy. Experimental results demonstrate that anti-PageRank weighting with author-count normalization significantly outperforms uniform weighting, maintaining high argument coverage even under coordinated attacks. The study further uncovers systematic relationships among creativity rate, recommendation volume, argument density, group size, and their joint effects on coverage and diversity.

Abstract

Deliberative polling promises to improve collective decision-making by exposing shareholders to a broad range of arguments before they vote. Yet ensuring that every voter encounters a representative sample of the reason space, the coverage problem, remains an open challenge, particularly at scale and in adversarial or strategically motivated electorates. This paper introduces a way of evaluating solutions using the LLM-based Agentic Bipolar Argumentation Simulator, grounded in a framework which formalises a poll as a six-tuple <Jend, Jopp, Ratt, Renh, VA, VR> of endorsing and opposing justifications, attack and enhance relations, and shareholder- and relation-weights. ABAS simulates N autonomous shareholder agents, each assigned a latent opinion according to desired distributions in [-1, 1], who sequentially vote, choose or author justifications, and optionally submit argumentation-graph links. The simulator implements recommendations that rank existing justifications by their observable endorsement mass. It evaluates the mechanism's success by coverage, namely the fraction of the corpus reason-tag set represented in the K recommendations presented to each shareholder, as a solution to the NP-hard Subsuming Justification Problem. Reported experiments characterise how creativity rate (pown), recommendation size (K), argumentation density (plinks), and population size (N) affect coverage and corpus diversity. In an authenticated electorate where Sybil attacks are impossible and only the relation graph is gameable, we stress-test the scoring with coordinated strategic voting attacks: a tag-flood attack collapses coverage, while author-count relation weighting through a reversed-PageRank rule resists the flood markedly better than uniform weights.

Problem

• deliberative polling
• coverage problem
• argumentation
• justification
• collective decision-making

Innovation

• Agentic Simulation
• Deliberative Polling
• Argumentation Framework
• Coverage Optimization
• Strategic Robustness