ML Anthology

Mechanism Design for Large Language Models (Extended Abstract)

Paul Dütting, Vahab Mirrokni, Renato Paes Leme, Haifeng Xu, Song Zuo
IJCAI 2025 pp. 10885-10890
doi:10.24963/IJCAI.2025/1210 /ijcai/2025/dutting2025ijcai-mechanism/

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.

PDF IJCAI Semantic Scholar

Cite

Text

Dütting et al. "Mechanism Design for Large Language Models (Extended Abstract)." International Joint Conference on Artificial Intelligence, 2025. doi:10.24963/IJCAI.2025/1210

Markdown

[Dütting et al. "Mechanism Design for Large Language Models (Extended Abstract)." International Joint Conference on Artificial Intelligence, 2025.](https://mlanthology.org/ijcai/2025/dutting2025ijcai-mechanism/) doi:10.24963/IJCAI.2025/1210

BibTeX

@inproceedings{dutting2025ijcai-mechanism,
  title     = {{Mechanism Design for Large Language Models (Extended Abstract)}},
  author    = {Dütting, Paul and Mirrokni, Vahab and Leme, Renato Paes and Xu, Haifeng and Zuo, Song},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {2025},
  pages     = {10885-10890},
  doi       = {10.24963/IJCAI.2025/1210},
  url       = {https://mlanthology.org/ijcai/2025/dutting2025ijcai-mechanism/}
}