PromptPrism: A Linguistically-Inspired Taxonomy for Prompts
Sullam Jeoung, Yueyan Chen, Yi Zhang, Shuai Wang, Haibo Ding, Lin Lee Cheong

TL;DR
PromptPrism introduces a linguistically-inspired taxonomy for analyzing prompts to improve large language model performance, offering a structured framework for prompt refinement, profiling, and sensitivity analysis.
Contribution
It presents a novel hierarchical taxonomy for prompt analysis based on linguistic concepts, bridging language understanding and LLM research.
Findings
PromptPrism improves prompt quality and model performance.
It enables comprehensive analysis of prompt datasets.
The framework quantifies prompt sensitivity to modifications.
Abstract
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
Taxonomy
TopicsTopic Modeling · Advanced Graph Neural Networks · Natural Language Processing Techniques
