提示词通过语义引导改变模型理解方式，而非仅提升性能
How Prompts Move Language Model Behavior: Frames, Salience, and Construal as Semantic Control
- 用框架激活、显著性控制、解释选择三机制解析提示词作用
- 提示词影响判断结果、证据使用和答案组织，方向可测
- 适合研究模型推理机制或优化提示设计的读者
提示工程被广泛用于调控大语言模型行为，但常被视为经验性技巧而非自然语言控制手段。本文提出一种认知语义框架，认为提示词作为语义条件，影响模型对输入的解读、信息突出和任务结构。通过框架激活、显著性控制和解释选择三个概念，在自然语言推理、论断验证和多跳问答任务中验证，提示词能引发可测量的行为变化，包括标签判断、证据使用和答案支持结构的改变，表明提示效果不仅在强度上不同，也在语义方向上存在差异。因此，本文将提示技术重新定位为分析指令如何驱动模型行为，而不仅是评估其是否提升性能。
原文摘要 · Abstract (English)
Prompt engineering is widely used to shape large language model behavior, yet it is often treated as a practical heuristic rather than as a form of natural-language control. This paper develops a cognitive-semantic account in which prompts function as semantic conditions on how a fixed model interprets inputs, foregrounds information, and structures tasks. We formalize this account through three notions -- frame activation, salience control, and construal selection -- and study them in natural language inference, claim verification, and multi-hop question answering. Across these settings, prompts produce measurable changes in label judgments, evidence use, and answer-support organization, showing that prompt effects differ not only in magnitude but also in semantic direction. The paper therefore reframes prompting as the analysis of how instructions move model behavior, rather than only whether they improve performance.
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。