用隐喻理论引导大模型，让推理更像人类。
Conceptual Metaphor Theory as a Prompting Paradigm for Large Language Models
- 用隐喻结构设计提示词，引导模型进行类人推理。
- 在多个任务中，准确率和表达清晰度显著提升。
- 适合需要深度理解与创造性推理的研究者。
我们提出将概念隐喻理论（CMT）作为增强大语言模型（LLM）复杂推理能力的认知提示范式。通过隐喻映射构建抽象思维结构，使模型更有效地处理和解释复杂概念。采用基于CMT的提示词，引导模型形成更系统、类人的推理路径。在涵盖领域特定推理、创造性洞察和隐喻理解的基准任务上，对比了Llama3.2、Phi3、Gemma2和Mistral四个原生模型及其CMT增强版本。使用Llama3.3 70B模型对响应进行自动评估。实验结果表明，CMT提示显著提升了推理准确性、表达清晰度和隐喻一致性，在所有任务中均优于基线模型。
原文摘要 · Abstract (English)
We introduce Conceptual Metaphor Theory (CMT) as a framework for enhancing large language models (LLMs) through cognitive prompting in complex reasoning tasks. CMT leverages metaphorical mappings to structure abstract reasoning, improving models' ability to process and explain intricate concepts. By incorporating CMT-based prompts, we guide LLMs toward more structured and human-like reasoning patterns. To evaluate this approach, we compare four native models (Llama3.2, Phi3, Gemma2, and Mistral) against their CMT-augmented counterparts on benchmark tasks spanning domain-specific reasoning, creative insight, and metaphor interpretation. Responses were automatically evaluated using the Llama3.3 70B model. Experimental results indicate that CMT prompting significantly enhances reasoning accuracy, clarity, and metaphorical coherence, outperforming baseline models across all evaluated tasks.
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。