TeamCMU at Touch\'e: Adversarial Co-Evolution for Advertisement Integration and Detection in Conversational Search

TL;DR

This paper presents a modular framework for integrating and detecting advertisements in conversational search systems powered by LLMs, using synthetic data and adversarial co-evolution to improve ad stealth and detection robustness.

Contribution

It introduces a novel adversarial co-evolution framework with a modular pipeline, synthetic data training, and classifier-guided ad integration strategies for conversational search.

Findings

High-performing ad classifiers trained on synthetic data.

Classifier-guided ad integration improves ad stealth.

Adversarial co-evolution enhances detection robustness.

Abstract

As conversational search engines increasingly adopt generation-based paradigms powered by Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG), the integration of advertisements into generated responses presents both commercial opportunities and challenges for user experience. Unlike traditional search, where advertisements are clearly delineated, generative systems blur the boundary between informational content and promotional material, raising concerns around transparency and trust. In this work, we propose a modular pipeline for advertisement management in RAG-based conversational systems, consisting of an ad-rewriter for seamless ad integration and a robust ad-classifier for detection. We leverage synthetic data to train high-performing classifiers, which are then used to guide two complementary ad-integration strategies: supervised fine-tuning of the ad-rewriter and a best-of-N sampling approach that selects the least detectable ad-integrated response among multiple candidates. Our evaluation focuses on two core questions: the effectiveness of ad classifiers in detecting diverse ad integration strategies, and the training methods that best support coherent, minimally intrusive ad insertion. Experimental results show that our ad-classifier, trained on synthetic advertisement data inspired by marketing strategies and enhanced through curriculum learning, achieves robust detection performance. Additionally, we demonstrate that classifier-guided optimization, through both fine-tuning and best-of-N sampling, significantly improves ad stealth, enabling more seamless integration. These findings contribute an adversarial co-evolution framework for developing more sophisticated ad-aware generative search systems and robust ad classifiers.