Data Auctions for Retrieval Augmented Generation

TL;DR

This paper explores data auction mechanisms for Retrieval Augmented Generation in AI, proposing a polynomial-time approximation algorithm with incentive compatibility, and demonstrating its effectiveness on real datasets.

Contribution

It introduces a novel auction framework for data selling in RAG, including a $(1-1/e)$ approximation algorithm and a data burning technique for incentive compatibility.

Findings

The welfare maximization problem is NP-hard even with two bidders.

The proposed algorithm achieves a $(1-1/e)$ approximation ratio.

Experiments show the algorithm outperforms baseline auction methods.

Abstract

We study the problem of data selling for Retrieval Augmented Generation (RAG) tasks in Generative AI applications. We model each buyer's valuation of a dataset with a natural coverage-based valuation function that increases with the inclusion of more relevant data points that would enhance responses to anticipated queries. Motivated by issues such as data control and prior-free revenue maximization, we focus on the scenario where each data point can be allocated to only one buyer. We show that the problem of welfare maximization in this setting is NP-hard even with two bidders, but design a polynomial-time $(1-1/e)$ approximation algorithm for any number of bidders. Unfortunately, however, this efficient allocation algorithm fails to be incentive compatible. The crux of our approach is a carefully tailored post-processing step called data burning which retains the $(1-1/e)$ approximation factor but achieves incentive compatibility. Our thorough experiments on synthetic and real-world image and text datasets demonstrate the practical effectiveness of our algorithm compared to popular baseline algorithms for combinatorial auctions.