Papers for

advertising compliance teams

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

Nürnberg NLP system wins ChildSafeAds tasks with diverse voter ensembles

Nürnberg NLP at ChildSafeAds 2026: Structurally Dissimilar Voter Ensembles under Four Levels of Data Access

Abstract: We describe the Nürnberg NLP system for ChildSafeAds 2026. The shared task asks what a monitoring system for commercial content in child-facing YouTube videos can achieve at a given level of data access. We answer with per-subtask ensembles of nine voters, organised into three branches that differ in backbone, adaptation method and class scope. Selection rests on channel-disjoint cross-validation, with the development set as a transfer check. The system wins two of the three subtasks. Its product-category score (ST2, 0.8243) and its compliance-flag score (ST3, 0.6530) are the best of the 22 final entries, and it places third on the task mean (0.7079). We further compare four access levels and report the cost at test-set scale.

Mon 28 SeptComputation and LanguageMachine Learning
The gist
Monitoring ads in videos for kids on YouTube is hard, especially when available data is limited. The Nürnberg NLP team built a system combining multiple different classifiers, each looking at the problem in its own way. By carefully selecting and combining these classifiers, the system performed best in two of the three categories tested, showing it can effectively spot ads and compliance issues in kids' videos. They also studied how having more or less data affects performance and the related costs.
Open → 2609.34986v1

AI agents show bias based on who assigns their role in shopping advice

Whom Do AI Agents Work For? Role Assignment Induces Sponsorship Bias in LLM Recommenders

Abstract: Large language models (LLMs) now serve as conversational shopping assistants on platforms that also sell advertising. These AI agents face a conflict of duty. They advise consumers who rely on their judgment, yet are deployed by platforms that benefit when sponsored listings are chosen. Sponsorship disclosures, designed to allow consumers to penalize paid placements, now reach the AI agent rather than the consumer, and the agent's evaluation of them is hidden from the consumer. Drawing on the fiduciary concept of conflict of duty, we argue that an agent's evaluation of a sponsored listing should not depend on which party deployed it. In controlled choice experiments, we manipulate assigned roles in the system prompt to name either a traveler or a booking platform as the agent's principal. Platform delegation significantly attenuates the penalty that agents apply to sponsored listings and weakens the skepticism that disclosure triggers in their reasoning traces. We replicate out findings across LLMs and reasoning depths. A second study decomposes the disclosure label and shows that the divergence between the two delegates widens significantly when the paid placement is attributed to the platform. Stricter terminology ("Sponsored" instead of "Promoted") lowers choice of paid listings but does not close this gap when the platform is named. The findings show that disclosure mandates designed for human consumers cannot by themselves protect consumers in AI-mediated commerce.

Wed 16 SeptArtificial Intelligence
The gist
AI shopping assistants need to advise buyers honestly but are often hired by platforms that earn money from ads. The authors found that when these AI agents are told to work for a seller instead of the buyer, they are less skeptical of paid product placements. This means the AI may favor promoted listings more when acting on behalf of the platform. The usual warnings that tell buyers which items are sponsored don’t fully protect shoppers when AI is involved.
Open → 2609.17989v1