Auctions with LLM Summaries
This work addresses auction design for LLM-based content summarization, which is incremental as it generalizes classic position auctions to LLM settings.
The authors tackled the problem of designing auctions for content placement within LLM-generated summaries, such as ad auctions where the display is a summary paragraph, by proposing a factorized framework that integrates an auction module and an LLM module via a prediction model to achieve welfare-maximizing outputs in an incentive-compatible manner, with theoretical analysis and synthetic experiments demonstrating feasibility and welfare comparisons.
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.