Narrative similarity requires reasoning over the deeper structural properties of stories - shared themes, causal progression, and outcomes - rather than surface-level lexical overlap. We describe AI-Monitors, our system for SemEval-2026 Task 4 (Track A), which determines which of two candidate stories is more narratively similar to a given anchor. We explore a progression of approaches - from embedding-based similarity to structured LLM prompting and ensemble construction - guided by four hypotheses about where narrative reasoning gains can be found. The final system achieves 75% test accuracy on 400 instances, ranking 3rd out of 47 systems and approaching the individual human annotator ceiling of 78%.Our key findings are: i) structured few-shot prompting substantially outperforms dense embedding similarity; ii) selecting ensemble components by how differently they make errors - rather than by accuracy alone - produces stronger predictions; and iii) how you describe an example to the model affects its predictions.

We describe AI-Monitors, our system for the ChildSafeAds shared task at NLLP@EMNLP 2026. The task labels sponsored segments in YouTube videos aimed at teenagers with their commercial type, product category and compliance-risk flags, and provides the input at four levels of increasing collection cost, from the free transcript to a crawled product page. Our system gives each sub-task its own input level and model: a fine-tuned ModernBERT-large encoder reading all four levels predicts commercial type and product category, the latter averaged with a TF-IDF classifier; a second encoder reading only the transcript predicts the compliance flags, averaged on the two disclosure flags with a QLoRA-tuned Qwen2.5-7B-Instruct that also reads the video metadata, before rules from the task’s taxonomy are applied. The system scored 0.6223 mean macro-F1 on the test set, 11th of 21 teams, and labels the 503 test instances in 25.5 GPU-minutes. We report the experiments behind each design choice: in our runs the crawled page helped product categorisation but not compliance flagging, the taxonomy’s definitions helped a prompted model while the legal provisions added little, and in two cases our validation procedure was misleading.

We describe the work carried out by our team, AI-Monitors, on the Binary Multilingual Machine-Generated Text Detection (Human vs. Machine) task at COLING 2025. This task aims to determine whether a given text is generated by a machine or authored by a human. We propose a lightweight, simple, and scalable approach using encoder models such as RoBERTa and XLM-R We provide an in-depth analysis based on our experiments. Our study found that carefully exploring fine-tuned parameters such as i) no. of training epochs, ii) maximum input size, iii) handling class imbalance etc., plays an important role in building an effective system to achieve good results and can significantly impact the underlying tasks. We found the optimum setting of these parameters can lead to a difference of about 5-6% in absolute terms for measure such as accuracy and F1 measure. The paper presents crucial insights into optimal parameter selection for fine-tuning RoBERTa and XLM-R based models to detect whether a given text is generated by a machine or a human.