PromptPrism: A Linguistically-Inspired Taxonomy for Prompts
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915751427833856 |
|---|---|
| author | Jeoung, Sullam Chen, Yueyan Zhang, Yi Wang, Shuai Ding, Haibo Cheong, Lin Lee |
| author_facet | Jeoung, Sullam Chen, Yueyan Zhang, Yi Wang, Shuai Ding, Haibo Cheong, Lin Lee |
| contents | Prompts are the interface for eliciting the capabilities of large language models (LLMs). Understanding their structure and components is critical for analyzing LLM behavior and optimizing performance. However, the field lacks a comprehensive framework for systematic prompt analysis and understanding. We introduce PromptPrism, a linguistically-inspired taxonomy that enables prompt analysis across three hierarchical levels: functional structure, semantic component, and syntactic pattern. By applying linguistic concepts to prompt analysis, PromptPrism bridges traditional language understanding and modern LLM research, offering insights that purely empirical approaches might miss. We show the practical utility of PromptPrism by applying it to three applications: (1) a taxonomy-guided prompt refinement approach that automatically improves prompt quality and enhances model performance across a range of tasks; (2) a multi-dimensional dataset profiling method that extracts and aggregates structural, semantic, and syntactic characteristics from prompt datasets, enabling comprehensive analysis of prompt distributions and patterns; (3) a controlled experimental framework for prompt sensitivity analysis by quantifying the impact of semantic reordering and delimiter modifications on LLM performance. Our experimental results validate the effectiveness of our taxonomy across these applications, demonstrating that PromptPrism provides a foundation for refining, profiling, and analyzing prompts. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_12592 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PromptPrism: A Linguistically-Inspired Taxonomy for Prompts Jeoung, Sullam Chen, Yueyan Zhang, Yi Wang, Shuai Ding, Haibo Cheong, Lin Lee Computation and Language Prompts are the interface for eliciting the capabilities of large language models (LLMs). Understanding their structure and components is critical for analyzing LLM behavior and optimizing performance. However, the field lacks a comprehensive framework for systematic prompt analysis and understanding. We introduce PromptPrism, a linguistically-inspired taxonomy that enables prompt analysis across three hierarchical levels: functional structure, semantic component, and syntactic pattern. By applying linguistic concepts to prompt analysis, PromptPrism bridges traditional language understanding and modern LLM research, offering insights that purely empirical approaches might miss. We show the practical utility of PromptPrism by applying it to three applications: (1) a taxonomy-guided prompt refinement approach that automatically improves prompt quality and enhances model performance across a range of tasks; (2) a multi-dimensional dataset profiling method that extracts and aggregates structural, semantic, and syntactic characteristics from prompt datasets, enabling comprehensive analysis of prompt distributions and patterns; (3) a controlled experimental framework for prompt sensitivity analysis by quantifying the impact of semantic reordering and delimiter modifications on LLM performance. Our experimental results validate the effectiveness of our taxonomy across these applications, demonstrating that PromptPrism provides a foundation for refining, profiling, and analyzing prompts. |
| title | PromptPrism: A Linguistically-Inspired Taxonomy for Prompts |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2505.12592 |