AI Persuasive Framing in Collective Dilemmas

2026-06-26 · Anders Giovanni Møller, Alessia Galdeman, Arianna Pera, Luca Maria Aiello arxiv

AI agents are promising tools that can act as flexible behavioral nudges to enhance human cooperation in addressing large-scale societal problems. However, evidence on whether AI agents can effectively boost cooperation remains mixed. We recruited 1,283 participants to play iterated Collective Risk Games in small groups, testing whether AI assistants could nudge participants toward cooperation. By using persuasive framing personalized to each player's Social Value Orientation profile, the AI interventions significantly increased contributions and group success rates. These cooperative effects were short-lived, however, fading after the first few rounds. Strikingly, when the AI treatments were reconfigured to promote selfish behavior through exculpatory framing, the negative effects on contributions and group success were larger and substantially more persistent, particularly for personalized interventions. This asymmetry between prosocial and antisocial persuasion highlights the dual-use risks of AI systems designed to influence group behavior in collective action settings.

📄 PDF Abstract BibTeX arXiv:2606.27951

Code (0)

등록된 구현이 없습니다.

Strategic Behavior of Large Language Models: Game Structure vs. Contextual Framing

2023-09-12 · Nunzio Lorè, Babak Heydari

This paper investigates the strategic decision-making capabilities of three Large Language Models (LLMs): GPT-3.5, GPT-4, and LLaMa-2, within the framework of game theory. Utilizing four canonical two-player games -- Pri…

Decision Making Navigate

Reinforcement Learning of Cooperative Persuasive Dialogue Policies using Framing

2014-08-01 · COLING 2014 8 · Takuya Hiraoka, Graham Neubig, Sakriani Sakti, Tomoki Toda 외

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)Slot Filling

Personalized Emphasis Framing for Persuasive Message Generation

2016-07-29 · EMNLP 2016 11 · Tao Ding, SHimei Pan

In this paper, we present a study on personalized emphasis framing which can be used to tailor the content of a message to enhance its appeal to different individuals. With this framework, we directly model content selec…

Learning Incentive Structures for Cooperative Resilience in Multi-Agent Systems under Social Dilemmas

2026-01-29 · Manuela Chacon-Chamorro, Luis Felipe Giraldo, Nicanor Quijano arxiv

Multi-agent social dilemmas, such as the tragedy of the commons, capture settings where individual incentives conflict with collective well-being, making these systems highly vulnerable to collapse under disruptions. In …

Multi-agent Reinforcement Learning

A Storytelling Robot managing Persuasive and Ethical Stances via ACT-R: an Exploratory Study

2021-07-27 · Agnese Augello, Giuseppe Città, Manuel Gentile, Antonio Lieto

We present a storytelling robot, controlled via the ACT-R cognitive architecture, able to adopt different persuasive techniques and ethical stances while conversing about some topics concerning COVID-19. The main contrib…

Dialogue Management Management