PromptMN: Pseudo Prompting Language
Quick Answer
PromptMN is a pseudo-prompting domain-specific language that enhances human-AI interaction by annotating natural language with structured directives.
Quick Take
Tested on models like Claude Fable 5 and GPT-5.5, it effectively resolves complex instructions without fine-tuning, aiming to reduce ambiguity in software development workflows.
Key Points
- Introduces compact, %-prefixed directives for roles, goals, and constraints.
- Evaluated on models including Claude Fable 5 and GPT-5.5 with successful instruction resolution.
- Supports complex structures like conditionals and repetition without fine-tuning.
- Aims to reduce repair cycles in software development by clarifying human-to-AI interactions.
- Facilitates reverse prompt engineering for better alignment of user expectations.
Paper Resources
Source Excerpt
arXiv:2606. 17164v1 Announce Type: new Abstract: 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. In agentic and software development workflows, a misread at the first handoff can propagate through every step, since a significant portion of agent failures stem from context ambiguities rather than model limitations. …
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CL
See more →TriAgent: Divergence-Aware Committees for Cost-Efficient Financial Sentiment Analysis
TriAgent introduces a cost-efficient multi-agent system for financial sentiment analysis, combining VADER, FinBERT, and Qwen2.5. It achieves an F1 score of ~0.87 with significant savings of $9.3M/year at a 10M-user scale compared to GPT-4o-mini, while also detecting hallucinations with an AUC of 0.90.