用大模型自动识别隐喻，三种方法效果对比。
Metaphor identification using large language models: A comparison of RAG, prompt engineering, and fine-tuning
- 用检索增强生成、提示工程和微调三法试跑隐喻识别
- 微调法在全文本上达中位F1 0.79，表现最优
- 结果可辅助理论构建，适合语言学与认知研究者
隐喻是话语的普遍特征，也是研究认知、情感与意识形态的重要视角。然而，由于隐喻具有强上下文依赖性，大规模分析长期受限于人工标注。本研究探索大语言模型（LLMs）在全文隐喻识别中的自动化潜力。比较三种方法：(i) 检索增强生成（RAG），提供规则与示例让模型依规标注；(ii) 提示工程，设计任务特定指令；(iii) 微调，基于人工标注数据训练模型以优化性能。在提示工程中，测试零样本、少样本及思维链策略。结果显示，顶尖闭源大模型可实现高准确率，微调法达中位F1 0.79。人机输出对比发现，多数差异具系统性，反映隐喻理论中的经典模糊地带与概念挑战。研究建议大模型可部分自动化隐喻识别，并作为发展与完善识别协议及理论的实验平台。
原文摘要 · Abstract (English)
Metaphor is a pervasive feature of discourse and a powerful lens for examining cognition, emotion, and ideology. Large-scale analysis, however, has been constrained by the need for manual annotation due to the context-sensitive nature of metaphor. This study investigates the potential of large language models (LLMs) to automate metaphor identification in full texts. We compare three methods: (i) retrieval-augmented generation (RAG), where the model is provided with a codebook and instructed to annotate texts based on its rules and examples; (ii) prompt engineering, where we design task-specific verbal instructions; and (iii) fine-tuning, where the model is trained on hand-coded texts to optimize performance. Within prompt engineering, we test zero-shot, few-shot, and chain-of-thought strategies. Our results show that state-of-the-art closed-source LLMs can achieve high accuracy, with fine-tuning yielding a median F1 score of 0.79. A comparison of human and LLM outputs reveals that most discrepancies are systematic, reflecting well-known grey areas and conceptual challenges in metaphor theory. We propose that LLMs can be used to at least partly automate metaphor identification and can serve as a testbed for developing and refining metaphor identification protocols and the theory that underpins them.
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。