LLM-Auction trains LLMs to perform generative auctions for native advertising by aligning model outputs with an objective that balances advertiser value and user experience, proving monotonicity and incentive properties under a first-price rule.
If the answer (1) is flooded with too many ads or (2) contains a lot of irrelevant text related to ad insertion, this will severely damage the user experience
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.GT 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
LLM-Auction: Generative Auction towards LLM-Native Advertising
LLM-Auction trains LLMs to perform generative auctions for native advertising by aligning model outputs with an objective that balances advertiser value and user experience, proving monotonicity and incentive properties under a first-price rule.