paper-with-me

홈 › Papers

LangGPT: Rethinking Structured Reusable Prompt Design Framework for LLMs from the Programming Language

2024-02-26 · Ming Wang, Yuanzhong Liu, Xiaoyu Liang, Songlian Li, YiJie Huang, XiaoMing Zhang, Sijia Shen, Chaofeng Guan, Daling Wang, Shi Feng, Huaiwen Zhang, Yifei Zhang, Minghui Zheng, Chi Zhang

LLMs have demonstrated commendable performance across diverse domains. Nevertheless, formulating high-quality prompts to instruct LLMs proficiently poses a challenge for non-AI experts. Existing research in prompt engineering suggests somewhat scattered optimization principles and designs empirically dependent prompt optimizers. Unfortunately, these endeavors lack a structured design template, incurring high learning costs and resulting in low reusability. In addition, it is not conducive to the iterative updating of prompts. Inspired by structured reusable programming languages, we propose LangGPT, a dual-layer prompt design framework as the programming language for LLMs. LangGPT has an easy-to-learn normative structure and provides an extended structure for migration and reuse. Experiments illustrate that LangGPT significantly enhances the performance of LLMs. Moreover, the case study shows that LangGPT leads LLMs to generate higher-quality responses. Furthermore, we analyzed the ease of use and reusability of LangGPT through a user survey in our online community.

📄 PDF Abstract BibTeX arXiv:2402.16929

Code (4)

langgptai/LangGPT 공식 구현
sci-m-wang/langgpt-tools 공식 구현
sci-m-wang/minstrel
yzfly/langgpt

Tasks

Prompt Engineering

Similar Papers 제목 키워드 기반

Minstrel: Structural Prompt Generation with Multi-Agents Coordination for Non-AI Experts

2024-09-20 · Ming Wang, Yuanzhong Liu, Xiaoyu Liang, YiJie Huang 외

LLMs have demonstrated commendable performance across diverse domains. Nevertheless, formulating high-quality prompts to assist them in their work poses a challenge for non-AI experts. Existing research in prompt enginee…

Prompt Engineering

CoGen: Creation of Reusable UI Components in Figma via Textual Commands

2026-01-15 · Ishani Kanapathipillai, Obhasha Priyankara arxiv

The evolution of User Interface design has emphasized the need for efficient, reusable, and editable components to ensure an efficient design process. This research introduces CoGen, a system that uses machine learning t…

Rethinking LLMOps for Fraud and AML: Building a Compliance-Grade LLM Serving Stack

2026-05-11 · Prathamesh Vasudeo Naik, Naresh Dintakurthi, Yue Wang arxiv

Fraud detection and anti-money-laundering (AML) compliance are high-value domains for large language models (LLMs), but their serving requirements differ sharply from generic chat workloads. Compliance prompts are often …

Fraud Detection

Generalizable Self-Evolving Memory for Automatic Prompt Optimization

2026-03-23 · Guanbao Liang, Yuanchen Bei, Sheng Zhou, Yuheng Qin 외 arxiv

Automatic prompt optimization is a promising approach for adapting large language models (LLMs) to downstream tasks, yet existing methods typically search for a specific prompt specialized to a fixed task. This paradigm …

PromptMN: Pseudo Prompting Language

2026-06-15 · Enkhzol Dovdon arxiv

Prompting has become the primary interface between humans and generative AI, yet many natural language prompts remain fragile: roles, goals, constraints, and expected outputs are often buried in prose or left implicit. I…

Prompt Engineering