Research map / Large language models / AI and society
VietCheckMed: Explainable Regulatory Compliance Checking for Medical Advertisements on Vietnamese Social Media
Nguyen Thanh Tam, Khanh Quoc Tran, Dat Thanh Pham, Truong Phu Le, Nguyen Hoang Gia Han, Binh T. Nguyen
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add evidence retrieval from regulatory corpus (ablation) | VietCheckMed (Llama 3.3) · VietAestheticAds Healthcare | macro F1: 0.0171 -> 0.6624 | Improved |
| add evidence retrieval from regulatory corpus (ablation) | VietCheckMed (Llama 3.3) · VietAestheticAds Beauty | macro F1: 0.7429 -> 0.8586 | Improved |
| add medical glossary for claim normalization (ablation) | VietCheckMed (Llama 3.3) · VietAestheticAds Beauty | macro F1: 0.6480 -> 0.8586 | Improved |
| add medical glossary for claim normalization (ablation) | VietCheckMed (Llama 3.3) · VietAestheticAds Healthcare | macro F1: 0.6380 -> 0.6624 | Improved |
| add codified regulatory knowledge base for beauty salons (ablation) | VietCheckMed (Llama 3.3) · VietAestheticAds Beauty | macro F1: 0.5383 -> 0.8586 | Improved |
| give LLMs access to the regulatory corpus (grounding) (ablation) | Llama 3.3 · VietAestheticAds Healthcare | macro F1: 0.0171 -> 0.6624 | Improved |
| give grounding to DeepSeek V3 on Beauty (ablation) | DeepSeek V3 · VietAestheticAds Beauty | macro F1: 0.7308 -> 0.7351 | No clear effect |
| give grounding to Qwen2.5 on Beauty (ablation) | Qwen2.5 · VietAestheticAds Beauty | macro F1: 0.7525 -> 0.7496 | No clear effect |
| multiple advertised techniques instead of single technique | Llama 3.3 · VietAestheticAds Beauty | macro F1: 0.8906 -> 0.8504 | Hurt |
| multiple advertised techniques instead of single technique | Llama 3.3 · VietAestheticAds Healthcare | macro F1: 0.7080 -> 0.5829 | Hurt |
| switch domain from Beauty to Healthcare | Llama 3.3 · VietAestheticAds | macro F1: 0.8586 -> 0.6624 | Hurt |
Closest papers by meaning
- ViFactCheck: A New Benchmark Dataset and Methods for Multi-Domain News Fact-Checking In Vietnamese (AAAI 2025 · similarity 0.84)
- Simulating Viva Voce Examinations to Evaluate Clinical Reasoning in Large Language Models (NeurIPS 2025 · similarity 0.82)
- CARES: Comprehensive Evaluation of Safety and Adversarial Robustness in Medical LLMs (NeurIPS 2025 · similarity 0.82)
- CARE: Towards Clinical Accountability in Multi-Modal Medical Reasoning with an Evidence-Grounded Agentic Framework (ICLR 2026 · similarity 0.81)
- Trustworthy and Practical AI for Healthcare: A Guided Deferral System with Large Language Models (AAAI 2025 · similarity 0.81)
- CASE-Bench: Context-Aware SafEty Benchmark for Large Language Models (ICML 2025 · similarity 0.81)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
