arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2502.03418cs.CL
收藏

零样本提示中哪些词最重要?

Which Words Matter Most in Zero-Shot Prompts?

Brock University(布罗克大学);Dalhousie University(达尔豪斯大学);Emory University(埃默里大学)

Nikta Gohari Sadr, Sangmitra Madhusudan, Hassan Sajjad, Ali Emami

AI总结:

本文提出 ZIP 分数,通过受控扰动量化零样本指令提示中的词语重要性,并在多模型、多任务实验中揭示词语层级、模型差异及性能负相关规律,且以基准验证其优于 LIME。

摘要:

尽管“让我们一步一步思考”等零样本指令提示已经彻底改变了大型语言模型的性能,但一个根本问题仍未得到解答:究竟是哪些具体词语推动了其显著效果?我们提出 ZIP 分数(Zero-shot Importance of Perturbation,零样本扰动重要性),这是首个通过受控扰动来量化指令提示中单个词语重要性的系统性方法,扰动方式包括同义词替换、共同下义词替换和策略性删除。我们在四个旗舰模型、七个被广泛采用的提示以及多个任务领域上的分析揭示了四项关键发现:(1)存在任务特定的词语层级,数学问题更重视“step-by-step”,而推理任务更偏好“think”;(2)与开源替代模型相比,专有模型表现出与人类直觉更优的一致性;(3)名词在重要性排名中占主导地位,始终构成重要词语的大多数;(4)词语重要性与模型性能呈负相关,表明提示在模型最困难的地方影响最大。除揭示这些模式外,我们还通过20个带有预定关键词的验证提示,建立了首个用于提示可解释性的真值基准;在该基准上,ZIP 达到90%的准确率,而 LIME 为60%。我们的发现推进了提示科学,即研究语言如何塑造模型行为,同时为提示工程提供实践洞见,并促进对 LLM 中词语级效应的理论理解。

英文摘要:

While zero-shot instructional prompts like "Let's think step-by-step" have revolutionized Large Language Model performance, a fundamental question remains unanswered: which specific words drive their remarkable effectiveness? We introduce the ZIP score (Zero-shot Importance of Perturbation), the first systematic method to quantify individual word importance in instructional prompts through controlled perturbations including synonym replacement, co-hyponym substitution, and strategic removal. Our analysis across four flagship models, seven widely-adopted prompts, and multiple task domains reveals four key findings: (1) Task-specific word hierarchies exist where mathematical problems prioritize "step-by-step" while reasoning tasks favor "think"; (2) Proprietary models show superior alignment with human intuitions compared to open-source alternatives; (3) Nouns dominate importance rankings, consistently representing the majority of significant words; and (4) Word importance inversely correlates with model performance, indicating prompts have greatest impact where models struggle most. Beyond revealing these patterns, we establish the first ground-truth benchmark for prompt interpretability through 20 validation prompts with predetermined key words, where ZIP achieves 90% accuracy versus LIME's 60%. Our findings advance prompt science, the study of how language shapes model behavior, providing both practical insights for prompt engineering and theoretical understanding of word-level effects in LLMs.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑