Authors: K Hackenburg, BM Tappin, P Röttger, S Hale
Year: 2024
Published in: arXiv preprint arXiv ..., 2024 - arxiv.org
Institution: University of Oxford, The Alan Turing Institute, Royal Holloway, University of London, Bocconi University, Meedan
Research Area: LLM scaling laws, Political Persuasion, Large Language Models, AI Social Science
Discipline: Political Science, Artificial Intelligence
Persuasiveness of messages generated by large language models follows a log scaling law with diminishing returns as model size increases, and task completion appears to primarily drive this capability.
Methods: Generated 720 persuasive messages on 10 U.S. political issues using 24 language models of varying sizes; evaluated persuasiveness through a large-scale randomized survey experiment.
Key Findings: Persuasiveness of large language model-generated political messages across different model sizes.
Citations: 17
Sample Size: 25982
Authors: Beth Armstrong, Christian Reynolds, Gemma Bridge, Libby Oakden Changqiong Wang, Luca Panzone, Ximena Schmidt Rivera, Astrid Kause, Charles Ffoulkes, Coleman Krawczyk, Grant Miller, Stephen Serjeant
Year: 2021
Published in: Frontiers
Institution: Agricultural Development Advisory Service, Brunel University London, Leeds Beckett University, Newcastle University, Open University, Queen Mary University of London, The University of Sheffield, University of Leeds, University of London, University of Portsmouth, Zooniverse
Research Area: Food Knowledge, Citizen Science, Survey Methodology
Discipline: Food Science, Survey Methodology
Citations: 26
