Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.08910 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912581456756736 |
|---|---|
| author | Vu, Tung Nguyen, Lam Dao, Quynh |
| author_facet | Vu, Tung Nguyen, Lam Dao, Quynh |
| contents | The proliferation of Large Language Models (LLMs) in real-world applications poses unprecedented risks of generating harmful, biased, or misleading information to vulnerable populations including LGBTQ+ individuals, single parents, and marginalized communities. While existing safety approaches rely on post-hoc filtering or generic alignment techniques, they fail to proactively prevent harmful outputs at the generation source. This paper introduces PromptGuard, a novel modular prompting framework with our breakthrough contribution: VulnGuard Prompt, a hybrid technique that prevents harmful information generation using real-world data-driven contrastive learning. VulnGuard integrates few-shot examples from curated GitHub repositories, ethical chain-of-thought reasoning, and adaptive role-prompting to create population-specific protective barriers. Our framework employs theoretical multi-objective optimization with formal proofs demonstrating 25-30% analytical harm reduction through entropy bounds and Pareto optimality. PromptGuard orchestrates six core modules: Input Classification, VulnGuard Prompting, Ethical Principles Integration, External Tool Interaction, Output Validation, and User-System Interaction, creating an intelligent expert system for real-time harm prevention. We provide comprehensive mathematical formalization including convergence proofs, vulnerability analysis using information theory, and theoretical validation framework using GitHub-sourced datasets, establishing mathematical foundations for systematic empirical research. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_08910 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PromptGuard: An Orchestrated Prompting Framework for Principled Synthetic Text Generation for Vulnerable Populations using LLMs with Enhanced Safety, Fairness, and Controllability Vu, Tung Nguyen, Lam Dao, Quynh Computer Vision and Pattern Recognition Artificial Intelligence The proliferation of Large Language Models (LLMs) in real-world applications poses unprecedented risks of generating harmful, biased, or misleading information to vulnerable populations including LGBTQ+ individuals, single parents, and marginalized communities. While existing safety approaches rely on post-hoc filtering or generic alignment techniques, they fail to proactively prevent harmful outputs at the generation source. This paper introduces PromptGuard, a novel modular prompting framework with our breakthrough contribution: VulnGuard Prompt, a hybrid technique that prevents harmful information generation using real-world data-driven contrastive learning. VulnGuard integrates few-shot examples from curated GitHub repositories, ethical chain-of-thought reasoning, and adaptive role-prompting to create population-specific protective barriers. Our framework employs theoretical multi-objective optimization with formal proofs demonstrating 25-30% analytical harm reduction through entropy bounds and Pareto optimality. PromptGuard orchestrates six core modules: Input Classification, VulnGuard Prompting, Ethical Principles Integration, External Tool Interaction, Output Validation, and User-System Interaction, creating an intelligent expert system for real-time harm prevention. We provide comprehensive mathematical formalization including convergence proofs, vulnerability analysis using information theory, and theoretical validation framework using GitHub-sourced datasets, establishing mathematical foundations for systematic empirical research. |
| title | PromptGuard: An Orchestrated Prompting Framework for Principled Synthetic Text Generation for Vulnerable Populations using LLMs with Enhanced Safety, Fairness, and Controllability |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2509.08910 |