Understanding how news narratives frame entities is crucial for studying media's impact on societal perceptions of events. In this paper, we evaluate the zero-shot capabilities of large language models (LLMs) in classifying framing roles. Through systematic experimentation, we assess the effects of input context, prompting strategies, and task decomposition. Our findings show that a hierarchical approach of first identifying broad roles and then fine-grained roles, outperforms single-step classification. We also demonstrate that optimal input contexts and prompts vary across task levels, highlighting the need for subtask-specific strategies. We achieve a Main Role Accuracy of 89.4% and an Exact Match Ratio of 34.5%, demonstrating the effectiveness of our approach. Our findings emphasize the importance of tailored prompt design and input context optimization for improving LLM performance in entity framing.
@article{arxiv.2504.20469,
title = {Fane at SemEval-2025 Task 10: Zero-Shot Entity Framing with Large Language Models},
author = {Enfa Fane and Mihai Surdeanu and Eduardo Blanco and Steven R. Corman},
journal= {arXiv preprint arXiv:2504.20469},
year = {2025}
}
Comments
Accepted to The 19th International Workshop on Semantic Evaluation (Semeval 2025)