Skip to content
aiqbench takeAI Safety

aiqbench analysis

This shared task leverages large language models like GPT-5.x to automate the classification of commercial content and legal risk flags within YouTube videos targeting minors, addressing a critical gap in AI safety for children's media. By structuring data across four access levels—from transcripts to linked sales pages—the project provides an empirical framework for evaluating how effectively current systems can detect undisclosed promotions compared to traditional manual review costs. The findings highlight that nearly half of the analyzed content lacked proper platform disclosure labels, underscoring the urgent need for robust AI-driven compliance tools in this sector.
Source coveringarXiv
What this isA model's reading of the article and related coverage, written for aiqbench. Not the publisher's words.

ChildSafeAds Shared Task 2026: Commercial Content in Child-Facing YouTube Videos

arXiv2 min read

arXiv:2608.19165v1 Announce Type: new Abstract: ChildSafeAds is a shared task on commercial content in YouTube videos likely to reach children and teenagers. It contains 3,360 videos from 939 channels. Each instance begins with a segment submitted to SponsorBlock, an open-source crowdsourced browser extension whose users mark sponsor segments so that others can skip them. We pair the segment with its available transcript, video and channel information, and a sales or service page linked from the video description. Systems determine what kind of offer is being promoted (ST1), assign product categories (ST2), and identify legal risk flags (ST3). The evidence is divided into four cumulative access levels, from the transcript to the linked page, so results can be compared against the cost of collecting the data. 45.5\% of videos in our data failed to properly use the in-platform ad disclosure method (the ``Includes paid promotion'' label). GPT-5.4 produced the labels after the expert organiser team reviewed samples and iterated on the taxonomy, prompts and model choices. GPT-5.6-luna independently labelled the development set. This report describes the task, data and evaluation. An updated version will add participating systems and shared-task results.

Abstract:ChildSafeAds is a shared task on commercial content in YouTube videos likely to reach children and teenagers. It contains 3,360 videos from 939 channels. Each instance begins with a segment submitted to SponsorBlock, an open-source crowdsourced browser extension whose users mark sponsor segments so that others can skip them. We pair the segment with its available transcript, video and channel information, and a sales or service page linked from the video description. Systems determine what kind of offer is being promoted (ST1), assign product categories (ST2), and identify legal risk flags (ST3). The evidence is divided into four cumulative access levels, from the transcript to the linked page, so results can be compared against the cost of collecting the data. 45.5\% of videos in our data failed to properly use the in-platform ad disclosure method (the ``Includes paid promotion'' label). GPT-5.4 produced the labels after the expert organiser team reviewed samples and iterated on the taxonomy, prompts and model choices. GPT-5.6-luna independently labelled the development set. This report describes the task, data and evaluation. An updated version will add participating systems and shared-task results.

Computation and Language (cs.CL); Computers and Society (cs.CY)

arXiv:2608.19165 [cs.CL]

(or arXiv:2608.19165v1 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2608.19165 Focus to learn more arXiv-issued DOI via DataCite (pending registration)

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Full text under the publisher's open licence · 283 words

Related coverage