Cover Image

Fundamental Limits of Game-Theoretic LLM Alignment: Smith Consistency and Preference Matching

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Shi, Zhekun, Liu, Kaizhao, Long, Qi, Su, Weijie J., Xiao, Jiancong
Format:	Preprint
Published:	2025
Subjects:	Computer Science and Game Theory Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Statistical Impossibility and Possibility of Aligning LLMs with Human Preferences: From Condorcet Paradox to Nash Equilibrium
by: Liu, Kaizhao, et al.
Published: (2025)

Theoretical Tensions in RLHF: Reconciling Empirical Success with Inconsistencies in Social Choice Theory
by: Xiao, Jiancong, et al.
Published: (2025)

Distortion of AI Alignment: Does Preference Optimization Optimize for Preferences?
by: Gölz, Paul, et al.
Published: (2025)

Reinforcement Learning for Game-Theoretic Resource Allocation on Graphs
by: An, Zijian, et al.
Published: (2025)

Socially-Weighted Alignment: A Game-Theoretic Framework for Multi-Agent LLM Systems
by: Mumcu, Furkan, et al.
Published: (2026)

Attacking and Securing Community Detection: A Game-Theoretic Framework
by: Niu, Yifan, et al.
Published: (2025)

Distributional Alignment Games for Answer-Level Fine-Tuning
by: Mohri, Mehryar, et al.
Published: (2026)

Last-Iterate Convergence Properties of Regret-Matching Algorithms in Games
by: Cai, Yang, et al.
Published: (2023)

Accelerated Preference Elicitation with LLM-Based Proxies
by: Huang, David, et al.
Published: (2025)

MaMa: A Game-Theoretic Approach for Designing Safe Agentic Systems
by: Nöther, Jonathan, et al.
Published: (2026)

Double Oracle Neural Architecture Search for Game Theoretic Deep Learning Models
by: Aung, Aye Phyu Phyu, et al.
Published: (2024)

Learning the Expected Core of Strictly Convex Stochastic Cooperative Games
by: Tran, Nam Phuong, et al.
Published: (2024)

GTAlign: Game-Theoretic Alignment of LLM Assistants for Social Welfare
by: Zhu, Siqi, et al.
Published: (2025)

You Are the Best Reviewer of Your Own Papers: The Isotonic Mechanism
by: Su, Weijie
Published: (2022)

RuleSmith: Multi-Agent LLMs for Automated Game Balancing
by: Zeng, Ziyao, et al.
Published: (2026)

On the Limitations and Possibilities of Nash Regret Minimization in Zero-Sum Matrix Games under Noisy Feedback
by: Maiti, Arnab, et al.
Published: (2023)

Scale-Invariant Regret Matching and Online Learning with Optimal Convergence: Bridging Theory and Practice in Zero-Sum Games
by: Zhang, Brian Hu, et al.
Published: (2025)

Response Time Enhances Alignment with Heterogeneous Preferences
by: Echenique, Federico, et al.
Published: (2026)

Market Games for Generative Models: Equilibria, Welfare, and Strategic Entry
by: Wei, Xiukun, et al.
Published: (2026)

Bandits with Preference Feedback: A Stackelberg Game Perspective
by: Pásztor, Barna, et al.
Published: (2024)

How Sampling Shapes LLM Alignment: From One-Shot Optima to Iterative Dynamics
by: Chen, Yurong, et al.
Published: (2026)

Convergence of Regret Matching in Potential Games and Constrained Optimization
by: Anagnostides, Ioannis, et al.
Published: (2025)

Fundamental Bounds on Online Strategic Classification
by: Ahmadi, Saba, et al.
Published: (2023)

Continuous-Time Analysis of Heavy Ball Momentum in Min-Max Games
by: Feng, Yi, et al.
Published: (2025)

Regulation Games for Trustworthy Machine Learning
by: Yaghini, Mohammad, et al.
Published: (2024)

Last-iterate Convergence Separation between Extra-gradient and Optimism in Constrained Periodic Games
by: Feng, Yi, et al.
Published: (2024)

Learning in Markov Games with Adaptive Adversaries: Policy Regret, Fundamental Barriers, and Efficient Algorithms
by: Nguyen-Tang, Thanh, et al.
Published: (2024)

The Power of Regularization in Solving Extensive-Form Games
by: Liu, Mingyang, et al.
Published: (2022)

LLM-Powered Preference Elicitation in Combinatorial Assignment
by: Soumalias, Ermis, et al.
Published: (2025)

Two-sided Competing Matching Recommendation Markets With Quota and Complementary Preferences Constraints
by: Li, Yuantong, et al.
Published: (2023)

Towards Performatively Stable Equilibria in Decision-Dependent Games for Arbitrary Data Distribution Maps
by: Zhong, Guangzheng, et al.
Published: (2025)

Swim till You Sink: Computing the Limit of a Game
by: Hakim, Rashida, et al.
Published: (2024)

Offline Two-Player Zero-Sum Markov Games with KL Regularization
by: Chen, Claire, et al.
Published: (2026)

On the Decomposition of Differential Game
by: Zhou, Nanxiang, et al.
Published: (2024)

Regularized Online RLHF with Generalized Bilinear Preferences
by: Lee, Junghyun, et al.
Published: (2026)

Proportional Aggregation of Preferences for Sequential Decision Making
by: Chandak, Nikhil, et al.
Published: (2023)

Shapley Machine: A Game-Theoretic Framework for N-Agent Ad Hoc Teamwork
by: Wang, Jianhong, et al.
Published: (2025)

Learning in Structured Stackelberg Games
by: Balcan, Maria-Florina, et al.
Published: (2025)

Learning to Steer Learners in Games
by: Zhang, Yizhou, et al.
Published: (2025)

Corrupted Learning Dynamics in Games
by: Tsuchiya, Taira, et al.
Published: (2024)