@inproceedings{r-etal-2025-tartantritons,
    title = "{T}artan{T}ritons at {S}em{E}val-2025 Task 10: Multilingual Hierarchical Entity Classification and Narrative Reasoning using Instruct-Tuned {LLM}s",
    author = "R, Raghav  and
      Vemali, Adarsh Prakash  and
      Aswal, Darpan  and
      Ramesh, Rahul  and
      Tusham, Parth  and
      Rishi, Pranaya",
    editor = "Rosenthal, Sara  and
      Ros{\'a}, Aiala  and
      Ghosh, Debanjan  and
      Zampieri, Marcos",
    booktitle = "Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/transition-to-people-yaml/2025.semeval-1.255/",
    pages = "1964--1973",
    ISBN = "979-8-89176-273-2",
    abstract = "In today{'}s era of abundant online news, tackling the spread of deceptive content and manipulative narratives has become crucial. This paper details our system for SemEval-2025 Task 10, focusing on Subtasks 1 (Entity Framing) and 3 (Narrative Extraction). We instruct-tuned quantized Microsoft{'}s Phi-4 model, incorporating prompt engineering techniques to enhance performance. Our approach involved experimenting with various LLMs, including LLaMA, Phi-4, RoBERTa, and XLM-R, utilizing both quantized large models and non-quantized small models. To improve accuracy, we employed structured prompts, iterative refinement with retry mechanisms, and integrated label taxonomy information. For subtask 1, we also fine-tuned a RoBERTa classifier to predict main entity roles before classifying the fine-grained roles with Phi-4 for the English language. For subtask 3, we instruct-tuned Phi-4 to generate structured explanations, incorporating details about the article and its dominant narrative. Our system achieves competitive results in Hindi and Russian for Subtask 1."
}