# Commercial Persuasion in AI-Mediated Conversations

arXiv: https://arxiv.org/abs/2604.04263 · HTML: https://mlsanity.com/paper/2604.04263/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 1 of its 86 references that are in the map.
- First posted on arXiv 5 Apr 2026.

## Builds on (most cited first, 1 of 1)

- [Lies, Damned Lies, and Distributional Language Statistics: Persuasion and Deception with Large Language Models](https://mlsanity.com/paper/2412.17128/) (2024)

## Built on by (most cited first, 7 of 7)

- [Deep-Research Agents Can Be Poisoned via User-Generated Content](https://mlsanity.com/paper/2605.24245/) (2026)
- [Using Cognitive Models to Improve Language Model Simulation of Human Persuasion Games](https://mlsanity.com/paper/2606.17657/) (2026)
- [Generative AI Advertising as a Problem of Trustworthy Commercial Intervention](https://mlsanity.com/paper/2605.18673/) (2026)
- [TourMart: A Parametric Audit Instrument for Commission Steering in LLM Travel Agents](https://mlsanity.com/paper/2605.10440/) (2026)
- [AI Watchdog: Agent Interfaces for Detecting and Defending Against Manipulative Dark Patterns in AI Conversations](https://mlsanity.com/paper/2608.21841/) (2026)
- [Selective Elicitation as a Commercial Influence Channel: A Reproducible Synthetic Shopping-Agent Stress Test](https://mlsanity.com/paper/2609.36614/) (2026)
- [Who Is Your Agent Serving? Provider-Side Indirect Prompt Injection in Proactive Agents](https://mlsanity.com/paper/2610.05266/) (2026)

## Abstract (arXiv)

As Large Language Models (LLMs) become a primary interface between users and the web, companies face growing economic incentives to embed commercial influence into AI-mediated conversations. We present two preregistered experiments (N = 2,012) in which participants selected a book to receive from a large eBook catalog using either a traditional search engine or a conversational LLM agent powered by one of five frontier models. Unbeknownst to participants, a fifth of all products were randomly designated as sponsored and promoted in different ways. We find that LLM-driven persuasion nearly triples the rate at which users select sponsored products compared to traditional search placement (61.2% vs. 22.4%), while the vast majority of participants fail to detect any promotional steering. Explicit "Sponsored" labels do not significantly reduce persuasion, and instructing the model to conceal its intent makes its influence nearly invisible (detection accuracy < 10%). Altogether, our results indicate that conversational AI can covertly redirect consumer choices at scale, and that existing transparency mechanisms may be insufficient to protect users.