大模型能理解词语在语境中的语义框架，无需标注也能准确识别。
Do LLMs Encode Frame Semantics? Evidence from Frame Identification
- 用提示词让大模型识别词语的语义框架，不依赖标注数据。
- 微调后在本领域准确率显著提升，跨领域也表现良好。
- 能生成合理语义定义，说明内部已掌握框架知识。
我们研究大语言模型是否隐含语义框架知识，聚焦于框架识别这一核心挑战——即根据上下文为目标词选择合适的语义框架。基于 FrameNet 词汇资源，我们在提示推理下评估模型表现，发现其无需显式监督即可有效完成框架识别。通过在 FrameNet 数据上微调模型，域内准确率大幅提升，且在跨域基准上仍保持良好泛化能力。进一步分析表明，模型能生成语义连贯的框架定义，体现出对语义框架的内在理解。
原文摘要 · Abstract (English)
We investigate whether large language models encode latent knowledge of frame semantics, focusing on frame identification, a core challenge in frame semantic parsing that involves selecting the appropriate semantic frame for a target word in context. Using the FrameNet lexical resource, we evaluate models under prompt-based inference and observe that they can perform frame identification effectively even without explicit supervision. To assess the impact of task-specific training, we fine-tune the model on FrameNet data, which substantially improves in-domain accuracy while generalizing well to out-of-domain benchmarks. Further analysis shows that the models can generate semantically coherent frame definitions, highlighting the model's internalized understanding of frame semantics.
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。