paper-with-me

홈 › Papers

Do LLMs trust AI regulation? Emerging behaviour of game-theoretic LLM agents

2025-04-11 · Alessio Buscemi, Daniele Proverbio, Paolo Bova, Nataliya Balabanova, Adeela Bashir, Theodor Cimpeanu, Henrique Correia da Fonseca, Manh Hong Duong, Elias Fernandez Domingos, Antonio M. Fernandes, Marcus Krellner, Ndidi Bianca Ogbo, Simon T. Powers, Fernando P. Santos, Zia Ush Shamszaman, Zhao Song, Alessandro Di Stefano, The Anh Han

There is general agreement that fostering trust and cooperation within the AI development ecosystem is essential to promote the adoption of trustworthy AI systems. By embedding Large Language Model (LLM) agents within an evolutionary game-theoretic framework, this paper investigates the complex interplay between AI developers, regulators and users, modelling their strategic choices under different regulatory scenarios. Evolutionary game theory (EGT) is used to quantitatively model the dilemmas faced by each actor, and LLMs provide additional degrees of complexity and nuances and enable repeated games and incorporation of personality traits. Our research identifies emerging behaviours of strategic AI agents, which tend to adopt more "pessimistic" (not trusting and defective) stances than pure game-theoretic agents. We observe that, in case of full trust by users, incentives are effective to promote effective regulation; however, conditional trust may deteriorate the "social pact". Establishing a virtuous feedback between users' trust and regulators' reputation thus appears to be key to nudge developers towards creating safe AI. However, the level at which this trust emerges may depend on the specific LLM used for testing. Our results thus provide guidance for AI regulation systems, and help predict the outcome of strategic LLM agents, should they be used to aid regulation itself.

📄 PDF Abstract BibTeX arXiv:2504.08640

Code (0)

등록된 구현이 없습니다.

Tasks

Large Language Model

Methods 이 논문이 사용한 방법론

ADOPT Please enter a description about the method here

Similar Papers 제목 키워드 기반

Media and responsible AI governance: a game-theoretic and LLM analysis

2025-03-12 · Nataliya Balabanova, Adeela Bashir, Paolo Bova, Alessio Buscemi 외

This paper investigates the complex interplay between AI developers, regulators, users, and the media in fostering trustworthy AI systems. Using evolutionary game theory and large language models (LLMs), we model the str…

Trust as Monitoring: Evolutionary Dynamics of User Trust and AI Developer Behaviour

2026-03-25 · Adeela Bashir, Zhao Song, Ndidi Bianca Ogbo, Nataliya Balabanova 외 arxiv

AI safety is an increasingly urgent concern as the capabilities and adoption of AI systems grow. Existing evolutionary models of AI governance have primarily examined incentives for safe development and effective regulat…

Reinforcement Learning

Social physics in the age of artificial intelligence

2026-03-04 · The Anh Han, Joel Z. Leibo, Tom Lenaerts, Iyad Rahwan 외 arxiv

Artificial intelligence (AI) systems are rapidly becoming more capable, autonomous, and deeply embedded in social life. As humans increasingly interact, cooperate, and compete with AI, we move from purely human societies…

Regulation Games for Trustworthy Machine Learning

2024-02-05 · Mohammad Yaghini, Patty Liu, Franziska Boenisch, Nicolas Papernot

Existing work on trustworthy machine learning (ML) often concentrates on individual aspects of trust, such as fairness or privacy. Additionally, many techniques overlook the distinction between those who train ML models …

FairnessGender Classification

Trust AI Regulation? Discerning users are vital to build trust and effective AI regulation

2024-03-14 · Zainab Alalawi, Paolo Bova, Theodor Cimpeanu, Alessandro Di Stefano 외

There is general agreement that some form of regulation is necessary both for AI creators to be incentivised to develop trustworthy systems, and for users to actually trust those systems. But there is much debate about w…