Pragyananda Sahoo

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.

Mental health is a global concern, with many individuals suffering from dysfunction due to depression, anxiety, common mental disorders, daily stressors, alcohol and substance use issues, and psychoses. Marma therapy addresses both psychological and physical challenges using contemporary methods. This traditional Indian Ayurvedic practice involves treating specific areas of the body. Marma therapy effectively reduces stress, anxiety, sadness, fears, and phobias, as supported by numerous studies. We gather images of users and analyse them based on various characteristics, including body type (Vata, Pitta, Kapha), height, current symptoms, structure, and medical history. This study outlines a comprehensive methodology for providing personalised recommendations for marma points to individuals. This solution could significantly impact Ayurveda and mental health.

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.