Enregistré dans:
Détails bibliographiques
Auteurs principaux: Cao, Yuhan, Wang, Yu, Liu, Sitong, Li, Miao, Tao, Yixin, He, Tianxing
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2511.00847
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914279511293952
author Cao, Yuhan
Wang, Yu
Liu, Sitong
Li, Miao
Tao, Yixin
He, Tianxing
author_facet Cao, Yuhan
Wang, Yu
Liu, Sitong
Li, Miao
Tao, Yixin
He, Tianxing
contents The widespread adoption of Large Language Models (LLMs) through Application Programming Interfaces (APIs) induces a critical vulnerability: the potential for dishonest manipulation by service providers. This manipulation can manifest in various forms, such as secretly substituting a proclaimed high-performance model with a low-cost alternative, or inflating responses with meaningless tokens to increase billing. This work tackles the issue through the lens of algorithmic game theory and mechanism design. We are the first to propose a formal economic model for a realistic user-provider ecosystem, where a user can iteratively delegate $T$ queries to multiple model providers, and providers can engage in a range of strategic behaviors. As our central contribution, we prove that for a continuous strategy space and any $ε\in(0,\frac12)$, there exists an approximate incentive-compatible mechanism with an additive approximation ratio of $O(T^{1-ε}\log T)$, and a guaranteed quasi-linear second-best user utility. We also prove an impossibility result, stating that no mechanism can guarantee an expected user utility that is asymptotically better than our mechanism. Furthermore, we demonstrate the effectiveness of our mechanism in simulation experiments with real-world API settings.
format Preprint
id arxiv_https___arxiv_org_abs_2511_00847
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Pay for The Second-Best Service: A Game-Theoretic Approach Against Dishonest LLM Providers
Cao, Yuhan
Wang, Yu
Liu, Sitong
Li, Miao
Tao, Yixin
He, Tianxing
Computer Science and Game Theory
Artificial Intelligence
The widespread adoption of Large Language Models (LLMs) through Application Programming Interfaces (APIs) induces a critical vulnerability: the potential for dishonest manipulation by service providers. This manipulation can manifest in various forms, such as secretly substituting a proclaimed high-performance model with a low-cost alternative, or inflating responses with meaningless tokens to increase billing. This work tackles the issue through the lens of algorithmic game theory and mechanism design. We are the first to propose a formal economic model for a realistic user-provider ecosystem, where a user can iteratively delegate $T$ queries to multiple model providers, and providers can engage in a range of strategic behaviors. As our central contribution, we prove that for a continuous strategy space and any $ε\in(0,\frac12)$, there exists an approximate incentive-compatible mechanism with an additive approximation ratio of $O(T^{1-ε}\log T)$, and a guaranteed quasi-linear second-best user utility. We also prove an impossibility result, stating that no mechanism can guarantee an expected user utility that is asymptotically better than our mechanism. Furthermore, we demonstrate the effectiveness of our mechanism in simulation experiments with real-world API settings.
title Pay for The Second-Best Service: A Game-Theoretic Approach Against Dishonest LLM Providers
topic Computer Science and Game Theory
Artificial Intelligence
url https://arxiv.org/abs/2511.00847