Avinava Dubey
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Interests
Avinava Dubey has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Aranyak Mehta
Google Research, Mountain View, CA, USA
1 shared publication - Di Wang
Google Research, Mountain View, CA, USA
1 shared publication - Rahul Kidambi
Google Research, Mountain View, CA, USA
1 shared publication - Zhe Feng
Google Research, Mountain View, CA, USA
1 shared publication
Latest Publications
- Open Access
- 24 August 2024
- Published by Association for Computing Machinery (ACM)
- p. 713-722
Auctions with LLM Summaries
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.
- 24 August 2024
- Published by Association for Computing Machinery (ACM)
- p. 713-722
Open AccessAuctions with LLM Summaries
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.