用大模型零样本识别新闻中实体的叙事角色，效果显著。
Fane at SemEval-2025 Task 10: Zero-Shot Entity Framing with Large Language Models
- 分步识别：先定大类角色，再细化具体角色
- 主角色准确率达89.4%，精确匹配率34.5%
- 不同任务层级需定制提示词和上下文
理解新闻叙事如何塑造实体形象，对研究媒体对社会认知的影响至关重要。本文评估大语言模型（LLMs）在零样本场景下分类叙事角色的能力。通过系统实验，考察输入上下文、提示策略及任务分解的影响。结果表明，先识别宽泛角色再细化具体角色的分层方法优于单步分类。同时发现，最优输入上下文与提示策略随任务层级而异，凸显子任务特异性策略的重要性。最终实现主角色准确率89.4%、精确匹配率34.5%，验证了该方法的有效性。研究强调针对实体叙事角色识别任务，需定制化提示设计与输入上下文优化。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。