# N"urnberg NLP at ChildSafeAds 2026: Structurally Dissimilar Voter Ensembles under Four Levels of Data Access

arXiv: https://arxiv.org/abs/2609.34986 · HTML: https://mlsanity.com/paper/2609.34986/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 34 references that are in the map.
- First posted on arXiv 28 Sep 2026.

## Builds on (most cited first, 18 of 18)

- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [CLAUDETTE: an Automated Detector of Potentially Unfair Clauses in Online Terms of Service](https://mlsanity.com/paper/1805.01217/) (2018)
- [Seq vs Seq: An Open Suite of Paired Encoders and Decoders](https://mlsanity.com/paper/2507.11412/) (2025)
- [EuroBERT: Scaling Multilingual Encoders for European Languages](https://mlsanity.com/paper/2503.05500/) (2025)
- [On the Ethical Limits of Natural Language Processing on Legal Text](https://mlsanity.com/paper/2105.02751/) (2021)
- [Deconfounding Legal Judgment Prediction for European Court of Human Rights Cases Towards Better Alignment with Experts](https://mlsanity.com/paper/2210.13836/) (2022)
- [Disturbed YouTube for Kids: Characterizing and Detecting Inappropriate Videos Targeting Young Children](https://mlsanity.com/paper/1901.07046/) (2019)
- [An Empirical Study of Affiliate Marketing Disclosures on YouTube and Pinterest](https://mlsanity.com/paper/1803.08488/) (2018)
- [Characterising and Detecting Sponsored Influencer Posts on Instagram](https://mlsanity.com/paper/2011.05757/) (2020)
- [Across Platforms and Languages: Dutch Influencers and Legal Disclosures on Instagram, YouTube and TikTok](https://mlsanity.com/paper/2407.12451/) (2024)
- [YouTubers Not madeForKids: Detecting Channels Sharing Inappropriate Videos Targeting Children](https://mlsanity.com/paper/2205.13885/) (2022)
- [Influencer Self-Disclosure Practices on Instagram: A Multi-Country Longitudinal Study](https://mlsanity.com/paper/2407.09202/) (2024)
- [Evaluating LLM-Generated Legal Explanations for Regulatory Compliance in Social Media Influencer Marketing](https://mlsanity.com/paper/2510.08111/) (2025)
- [AI Systems in Text-Based Online Counselling: Ethical Considerations Across Three Implementation Approaches](https://mlsanity.com/paper/2601.08878/) (2026)
- [Automated detection of dark patterns in cookie banners: how to do it poorly and why it is hard to do it any other way](https://mlsanity.com/paper/2204.11836/) (2022)
- [N"urnberg NLP at PsyDefDetect: Multi-Axis Voter Ensembles for Psychological Defence Mechanism Classification](https://mlsanity.com/paper/2605.07606/) (2026)
- [N"urnberg NLP @ GermEval Shared Task 2026: Harmful Content Detection in German Social Media through Error-Independent LLM Voters](https://mlsanity.com/paper/2608.22246/) (2026)
- [CAIA in Practice: Field Evaluation of an AI-Assisted Support System for Text-Based Online Counselling](https://mlsanity.com/paper/2608.22251/) (2026)

## Abstract (arXiv)

We describe the N"urnberg 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.