Mechanism Design for Large Language Models (Extended Abstract)

Dütting, Paul; Mirrokni, Vahab; Paes Leme, Renato; Xu, Haifeng; Zuo, Song

doi:10.24963/ijcai.2025/1210

Mechanism Design for Large Language Models (Extended Abstract)

Paul Dütting, Vahab Mirrokni, Renato Paes Leme, Haifeng Xu, Song Zuo

Download BibTeX Cite

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence. Sister Conferences Best Papers. Pages 10885-10890.

https://doi.org/10.24963/ijcai.2025/1210

Keywords

Sister Conferences Best Papers: Multidisciplinary Topics and Applications
Sister Conferences Best Papers: Game Theory and Economic Paradigms
Sister Conferences Best Papers: Machine Learning

Abstract

We investigate auction mechanisms for AI-generated content, focusing on applications like ad creative generation. In our model, agents' preferences over stochastically generated content are encoded as large language models (LLMs).

We propose an auction format that operates on a token-by-token basis, and allows LLM agents to influence content creation through single dimensional bids. We formulate two desirable incentive properties and prove their equivalence to a monotonicity condition on output aggregation. This equivalence enables a second-price rule design, even absent explicit agent valuation functions. Our design is supported by demonstrations on a publicly available LLM.

Paul Dütting, Vahab Mirrokni, Renato Paes Leme, Haifeng Xu, and Song Zuo. 2025. Mechanism Design for Large Language Models (Extended Abstract). In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25. IJCAI, 10885–10890. https://doi.org/10.24963/ijcai.2025/1210

@inproceedings{ijcai2025p1210,
  title     = {Mechanism Design for Large Language Models (Extended Abstract)},
  author    = {Dütting, Paul and Mirrokni, Vahab and Paes Leme, Renato and Xu, Haifeng and Zuo, Song},
  booktitle = {Proceedings of the Thirty-Fourth International Joint Conference on
               Artificial Intelligence, {IJCAI-25}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {James Kwok},
  pages     = {10885--10890},
  year      = {2025},
  month     = {8},
  note      = {Sister Conferences Best Papers},
  doi       = {10.24963/ijcai.2025/1210},
  url       = {https://doi.org/10.24963/ijcai.2025/1210},
}

TY  - CPAPER
TI  - Mechanism Design for Large Language Models (Extended Abstract)
AU  - Dütting, Paul
AU  - Mirrokni, Vahab
AU  - Paes Leme, Renato
AU  - Xu, Haifeng
AU  - Zuo, Song
T2  - Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2025
SP  - 10885
EP  - 10890
DO  - 10.24963/ijcai.2025/1210
UR  - https://doi.org/10.24963/ijcai.2025/1210
ER  -