Auctions with LLM Summaries
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913311164989440 |
|---|---|
| author | Dubey, Kumar Avinava Feng, Zhe Kidambi, Rahul Mehta, Aranyak Wang, Di |
| author_facet | Dubey, Kumar Avinava Feng, Zhe Kidambi, Rahul Mehta, Aranyak Wang, Di |
| contents | We study an auction setting in which bidders bid for placement of their content within a summary generated by a large language model (LLM), e.g., an ad auction in which the display is a summary paragraph of multiple ads. This generalizes the classic ad settings such as position auctions to an LLM generated setting, which allows us to handle general display formats. We propose a novel factorized framework in which an auction module and an LLM module work together via a prediction model to provide welfare maximizing summary outputs in an incentive compatible manner. We provide a theoretical analysis of this framework and synthetic experiments to demonstrate the feasibility and validity of the system together with welfare comparisons. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_08126 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Auctions with LLM Summaries Dubey, Kumar Avinava Feng, Zhe Kidambi, Rahul Mehta, Aranyak Wang, Di Computer Science and Game Theory Artificial Intelligence We study an auction setting in which bidders bid for placement of their content within a summary generated by a large language model (LLM), e.g., an ad auction in which the display is a summary paragraph of multiple ads. This generalizes the classic ad settings such as position auctions to an LLM generated setting, which allows us to handle general display formats. We propose a novel factorized framework in which an auction module and an LLM module work together via a prediction model to provide welfare maximizing summary outputs in an incentive compatible manner. We provide a theoretical analysis of this framework and synthetic experiments to demonstrate the feasibility and validity of the system together with welfare comparisons. |
| title | Auctions with LLM Summaries |
| topic | Computer Science and Game Theory Artificial Intelligence |
| url | https://arxiv.org/abs/2404.08126 |