REVIEW 5 cited by
Truthful Aggregation of LLMs with an Application to Online Advertising
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
The next frontier of online advertising is revenue generation from LLM-generated content. We consider a setting where advertisers aim to influence the responses of an LLM to align with their interests, while platforms seek to maximize advertiser value and ensure user satisfaction. The challenge is that advertisers' preferences generally conflict with those of the user, and advertisers may misreport their preferences. To address this, we introduce MOSAIC, an auction mechanism that ensures that truthful reporting is a dominant strategy for advertisers and that aligns the utility of each advertiser with their contribution to social welfare. Importantly, the mechanism operates without LLM fine-tuning or access to model weights and provably converges to the output of the optimally fine-tuned LLM as computational resources increase. Additionally, it can incorporate contextual information about advertisers, which significantly improves social welfare. Through experiments with a publicly available LLM, we show that MOSAIC leads to high advertiser value and platform revenue with low computational overhead. While our motivating application is online advertising, our mechanism can be applied in any setting with monetary transfers, making it a general-purpose solution for truthfully aggregating the preferences of self-interested agents over LLM-generated replies.
Forward citations
Cited by 5 Pith papers
-
PILA: Plug-and-Play Insertion for LLM-native Advertising
Ads can be inserted into LLM answers after the fact by an external rewriter model, improving measured ad quality without retraining or modifying the base chatbot.
-
Position Auctions in AI-Generated Content
New mechanism-design results for position auctions with context-dependent click-through rates under multinomial logit and cascade user models, with exact optimality in the MNL case and an O(log m) approximation in the...
-
LLM-Powered Preference Elicitation in Combinatorial Assignment
An LLM proxy that answers comparison queries from one free-text preference description improves simulated course allocation efficiency by up to 22%.
-
TeamCMU at Touch\'e: Adversarial Co-Evolution for Advertisement Integration and Detection in Conversational Search
A system trained with marketing-inspired synthetic data and curriculum learning detects embedded ads well, while classifier-guided rewriting (best-of-N and fine-tuning) makes generated ads significantly harder to detect.
-
Learning Truthful Mechanisms without Discretization
TEDI learns truthful, revenue-maximizing mechanisms by representing prices as continuous partially convex functions and training them with a covariance gradient trick and Langevin sampling, without discretizing outcomes.
Discussion (0). Continue with ORCID to comment.