Image de couverture de livre

Why AI Safety Requires Uncertainty, Incomplete Preferences, and Non-Archimedean Utilities

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Benavoli, Alessio, Facchini, Alessandro, Zaffalon, Marco
Format:	Preprint
Publié:	2025
Sujets:	Artificial Intelligence Computer Science and Game Theory
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Computing Voting Rules with Elicited Incomplete Votes
par: Halpern, Daniel, et autres
Publié: (2024)

Expected Utility Networks
par: La Mura, Pierfrancesco, et autres
Publié: (2013)

Reliable and Private Utility Signaling for Data Markets
par: Peng, Li, et autres
Publié: (2025)

Adaptive Preference Aggregation
par: Heymann, Benjamin
Publié: (2025)

Learning in Multi-Objective Public Goods Games with Non-Linear Utilities
par: Orzan, Nicole, et autres
Publié: (2024)

Multilevel Fair Allocation with Matroid-Rank Preferences
par: Lucet, Maxime, et autres
Publié: (2025)

A Revealed Preference Framework for AI Alignment
par: Suleymanov, Elchin
Publié: (2026)

Differential Voting: Loss Functions For Axiomatically Diverse Aggregation of Heterogeneous Preferences
par: An, Zhiyu, et autres
Publié: (2026)

Do Large Language Models Learn Human-Like Strategic Preferences?
par: Roberts, Jesse, et autres
Publié: (2024)

Heuristic Pathologies and Further Variance Reduction via Uncertainty Propagation in the AIVAT Family of Techniques
par: Kim, Juho, et autres
Publié: (2026)

Nash Equilibrium in Games on Graphs with Incomplete Preferences
par: Kulkarni, Abhishek N., et autres
Publié: (2024)

On the Impact of the Utility in Semivalue-based Data Valuation
par: Tamine, Mélissa, et autres
Publié: (2025)

A General Theory of Proportionality with Additive Utilities
par: Skowron, Piotr
Publié: (2026)

Engineering Social Optimality via Utility Shaping in Non-Cooperative Games under Incomplete Information and Imperfect Monitoring
par: Smith, David, et autres
Publié: (2025)

Collaborating with GenAI: Incentives and Replacements
par: Taitler, Boaz, et autres
Publié: (2025)

Data Sharing with a Generative AI Competitor
par: Taitler, Boaz, et autres
Publié: (2025)

Power and Limitations of Aggregation in Compound AI Systems
par: Ananthakrishnan, Nivasini, et autres
Publié: (2026)

Playing Large Games with Oracles and AI Debate
par: Chen, Xinyi, et autres
Publié: (2023)

Multiwinner Voting with Interval Preferences under Incomplete Information
par: Springham, Drew, et autres
Publié: (2025)

AI Testing Should Account for Sophisticated Strategic Behaviour
par: Kovarik, Vojtech, et autres
Publié: (2025)

Mechanism Design Is Not Enough: Prosocial Agents for Cooperative AI
par: Huang, Xuanqiang Angelo, et autres
Publié: (2026)

Ex Ante Evaluation of AI-Induced Idea Diversity Collapse
par: Azad, Nafis Saami, et autres
Publié: (2026)

The Backfiring Effect of Weak AI Safety Regulation
par: Laufer, Benjamin, et autres
Publié: (2025)

Incentives, Equilibria, and the Limits of Healthcare AI: A Game-Theoretic Perspective
par: Ercole, Ari
Publié: (2026)

Tell Me Why: Incentivizing Explanations
par: Srinivasan, Siddarth, et autres
Publié: (2025)

The Price of Paranoia: Robust Risk-Sensitive Cooperation in Non-Stationary Multi-Agent Reinforcement Learning
par: Ganguly, Deep Kumar, et autres
Publié: (2026)

Solving Urban Network Security Games: Learning Platform, Benchmark, and Challenge for AI Research
par: Zhuang, Shuxin, et autres
Publié: (2025)

Institutional AI: Governing LLM Collusion in Multi-Agent Cournot Markets via Public Governance Graphs
par: Syrnikov, Marcantonio Bracale, et autres
Publié: (2026)

Why Do LLMs Struggle in Strategic Play? Broken Links Between Observations, Beliefs, and Actions
par: Sobotka, Jan, et autres
Publié: (2026)

Online Test Synthesis From Requirements: Enhancing Reinforcement Learning with Game Theory
par: Sankur, Ocan, et autres
Publié: (2024)

LLM-Powered Preference Elicitation in Combinatorial Assignment
par: Soumalias, Ermis, et autres
Publié: (2025)

Bi-LSTM based Multi-Agent DRL with Computation-aware Pruning for Agent Twins Migration in Vehicular Embodied AI Networks
par: Wei, Yuxiang, et autres
Publié: (2025)

Bandits with Preference Feedback: A Stackelberg Game Perspective
par: Pásztor, Barna, et autres
Publié: (2024)

Can Media Act as a Soft Regulator of Safe AI Development? A Game Theoretical Analysis
par: da Fonseca, Henrique Correia, et autres
Publié: (2025)

Can LLMs effectively provide game-theoretic-based scenarios for cybersecurity?
par: Proverbio, Daniele, et autres
Publié: (2025)

Competition and Diversity in Generative AI
par: Raghavan, Manish
Publié: (2024)

Preferences Evolve And So Should Your Bandits: Bandits with Evolving States for Online Platforms
par: Khosravi, Khashayar, et autres
Publié: (2023)

Modeling the Economic Impacts of AI Openness Regulation
par: Qiu, Tori, et autres
Publié: (2025)

Path Dependence under Adaptive AI Delegation
par: Huang, Lingxiao, et autres
Publié: (2026)

Personality Modeling for Persuasion of Misinformation using AI Agent
par: Lou, Qianmin, et autres
Publié: (2025)