Do LLMs trust AI regulation? Emerging behaviour of game-theoretic LLM agents
- URL: http://arxiv.org/abs/2504.08640v1
- Date: Fri, 11 Apr 2025 15:41:21 GMT
- Title: Do LLMs trust AI regulation? Emerging behaviour of game-theoretic LLM agents
- Authors: 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,
- Abstract summary: This paper investigates the interplay between AI developers, regulators and users, modelling their strategic choices under different regulatory scenarios.<n>Our research identifies emerging behaviours of strategic AI agents, which tend to adopt more "pessimistic" stances than pure game-theoretic agents.
- Score: 61.132523071109354
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: 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.
Related papers
- FAIRGAME: a Framework for AI Agents Bias Recognition using Game Theory [51.96049148869987]
We present FAIRGAME, a Framework for AI Agents Bias Recognition using Game Theory.
We describe its implementation and usage, and we employ it to uncover biased outcomes in popular games among AI agents.
Overall, FAIRGAME allows users to reliably and easily simulate their desired games and scenarios.
arXiv Detail & Related papers (2025-04-19T15:29:04Z) - Media and responsible AI governance: a game-theoretic and LLM analysis [61.132523071109354]
This paper investigates the interplay between AI developers, regulators, users, and the media in fostering trustworthy AI systems.<n>Using evolutionary game theory and large language models (LLMs), we model the strategic interactions among these actors under different regulatory regimes.
arXiv Detail & Related papers (2025-03-12T21:39:38Z) - Can We Trust AI Agents? An Experimental Study Towards Trustworthy LLM-Based Multi-Agent Systems for AI Ethics [10.084913433923566]
This study examines how trustworthiness-enhancing techniques affect ethical AI output generation.
We design the prototype LLM-BMAS, where agents engage in structured discussions on real-world ethical AI issues.
Discussions reveal terms like bias detection, transparency, accountability, user consent, compliance, fairness evaluation, and EU AI Act compliance.
arXiv Detail & Related papers (2024-10-25T20:17:59Z) - Engineering Trustworthy AI: A Developer Guide for Empirical Risk Minimization [53.80919781981027]
Key requirements for trustworthy AI can be translated into design choices for the components of empirical risk minimization.
We hope to provide actionable guidance for building AI systems that meet emerging standards for trustworthiness of AI.
arXiv Detail & Related papers (2024-10-25T07:53:32Z) - Towards Trustworthy AI: A Review of Ethical and Robust Large Language Models [1.7466076090043157]
Large Language Models (LLMs) could transform many fields, but their fast development creates significant challenges for oversight, ethical creation, and building user trust.
This comprehensive review looks at key trust issues in LLMs, such as unintended harms, lack of transparency, vulnerability to attacks, alignment with human values, and environmental impact.
To tackle these issues, we suggest combining ethical oversight, industry accountability, regulation, and public involvement.
arXiv Detail & Related papers (2024-06-01T14:47:58Z) - Trust AI Regulation? Discerning users are vital to build trust and effective AI regulation [32.98110040460262]
We show that creating trustworthy AI and user trust requires regulators to be incentivised to regulate effectively.
We demonstrate the effectiveness of two mechanisms that can achieve this.
We then consider an alternative solution, where users can condition their trust decision on the effectiveness of the regulators.
arXiv Detail & Related papers (2024-03-14T15:56:39Z) - The Rise and Potential of Large Language Model Based Agents: A Survey [91.71061158000953]
Large language models (LLMs) are regarded as potential sparks for Artificial General Intelligence (AGI)
We start by tracing the concept of agents from its philosophical origins to its development in AI, and explain why LLMs are suitable foundations for agents.
We explore the extensive applications of LLM-based agents in three aspects: single-agent scenarios, multi-agent scenarios, and human-agent cooperation.
arXiv Detail & Related papers (2023-09-14T17:12:03Z) - Designing for Responsible Trust in AI Systems: A Communication
Perspective [56.80107647520364]
We draw from communication theories and literature on trust in technologies to develop a conceptual model called MATCH.
We highlight transparency and interaction as AI systems' affordances that present a wide range of trustworthiness cues to users.
We propose a checklist of requirements to help technology creators identify appropriate cues to use.
arXiv Detail & Related papers (2022-04-29T00:14:33Z) - The Sanction of Authority: Promoting Public Trust in AI [4.729969944853141]
We argue that public distrust of AI originates from the under-development of a regulatory ecosystem that would guarantee the trustworthiness of the AIs that pervade society.
We elaborate the pivotal role of externally auditable AI documentation within this model and the work to be done to ensure it is effective.
arXiv Detail & Related papers (2021-01-22T22:01:30Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.