This paper introduces an author-assisted mechanism, based on the Isotonic Mechanism, to improve the selection of best paper awards at large machine learning and AI conferences. It relaxes the common convexity assumption for author utility functions, ensuring truthfulness even with simpler monotonicity assumptions, and empirically demonstrates its effectiveness in improving award selection quality through simulations.

This paper introduces a formal model for designing and analyzing interactive platforms where Large Language Models (LLMs) offer sponsored clarifying follow-up prompts to ambiguous user queries. It investigates the trade-offs between end-to-end joint optimization and decoupled modular mechanisms, demonstrating that the VCG mechanism can achieve efficient and truthful outcomes in a unified system, while modular approaches suffer from unbounded strategic inefficiency.