AI for Enhancing Democratic Deliberation

Civic Technology Community Group,

Hello. I would like to share the following recent and interesting papers, datasets, and demos. AI systems can, increasingly, help communities to argue, to debate, to find common ground, to build consensus, and to validate their argumentative discourse and essays with respect to manuals of style.

AI Can Help Humans Find Common Ground in Democratic Deliberation
Michael Henry Tessler, Michiel A. Bakker, Daniel Jarrett, Hannah Sheahan, Martin J. Chadwick, Raphael Koster, Georgina Evans, et al.
https://www.science.org/doi/10.1126/science.adq2852

"Democracy, at its best, rests upon the free and equal exchange of views among people with diverse perspectives. Collective deliberation can be effectively supported by structured events, such as citizens’ assemblies, but such events are expensive, are difficult to scale, and can result in voices being heard unequally. This study investigates the potential of artificial intelligence (AI) to overcome these limitations, using AI mediation to help people find common ground on complex social and political issues."

OpenDebateEvidence: A Massive-Scale Argument Mining and Summarization Dataset
Allen Roush, Yusuf Shabazz, Arvind Balaji, Peter Zhang, Stefano Mezza, Markus Zhang, Sanjay Basu, Sriram Vishwanath, Mehdi Fatemi, and Ravid Shwartz-Ziv
https://paperswithcode.com/paper/opendebateevidence-a-massive-scale-argument

"We introduce OpenDebateEvidence, a comprehensive dataset for argument mining and summarization sourced from the American Competitive Debate community. This dataset includes over 3.5 million documents with rich metadata, making it one of the most extensive collections of debate evidence. OpenDebateEvidence captures the complexity of arguments in high school and college debates, providing valuable resources for training and evaluation. Our extensive experiments demonstrate the efficacy of fine-tuning state-of-the-art large language models for argumentative abstractive summarization across various methods, models, and datasets. By providing this comprehensive resource, we aim to advance computational argumentation and support practical applications for debaters, educators, and researchers. OpenDebateEvidence is publicly available to support further research and innovation in computational argumentation."

Omnipedia: Automating Article Review with the Manual of Style
Samuel J. Klein, Michael Zargham, Sayer Tindall, Alex Andonian
https://github.com/wikius/omnipedia
https://omnipedia-client.pages.dev/

"Omnipedia is a system and toolchain that streamlines the evaluation of articles against style guides using advanced language models (LMs). This system enhances the speed and consistency of article reviews, alleviating bottlenecks caused by manual evaluations."

"The core system converts style guides into actionable requirements, maps these requirements to articles, and provides detailed, contextual evaluations. Omnipedia visually overlays these evaluations on articles to highlight compliance and areas for improvement."


Best regards,
Adam Sobieski