s4nkar/klarki-prohibited-classifier

KlarKI — EU AI Act Article 5 Prohibited Practice Classifier

Binary classification — detects EU AI Act Article 5 prohibited AI practices

Part of KlarKI — a local-first EU AI Act + GDPR compliance auditor for German SMEs. All inference runs on-device. No data leaves your machine.

---

Model Overview

Property	Value
Base model	deepset/gbert-base
Architecture	Transformers — BertForSequenceClassification
Parameters	~110M parameters
Languages	German (primary), English
Training samples	1371 train / 243 validation
License	MIT
Part of	KlarKI audit pipeline

---

Quickstart

Option A — Via KlarKI (recommended)

Use this if you want the full audit pipeline. The download script places all 5 models exactly where KlarKI expects them.

git clone https://github.com/s4nkar/KlarKI-EU-AI-Act-compliance-auditor.git
cd KlarKI-EU-AI-Act-compliance-auditor
pip install huggingface-hub>=0.26.0
python scripts/download_pretrained.py --model prohibited
./run.sh up

Option B — Direct usage

from transformers import pipeline

classifier = pipeline("text-classification", model="s4nkar/klarki-prohibited-classifier")
result = classifier("The system assigns a social score to citizens based on their behaviour and personal characteristics.")
# Output: [{'label': 'prohibited', 'score': 0.99}]

---

Labels

Label	Description
prohibited	Describes a practice prohibited under Article 5 of the EU AI Act
not_prohibited	Does not describe a prohibited practice

---

Evaluation Results

Overall

Macro F1	Val samples
0.9794	243

Per-Class

Class	Precision	Recall	F1	Support
prohibited	1.0000	0.9590	0.9791	122
not_prohibited	0.9603	1.0000	0.9798	121

---

Training Details

Property	Value
Base model	deepset/gbert-base
Training epochs	5 (AdamW, early stopping)
Batch size	16
Data split	85% train / 15% validation, stratified, seed=42
Data generation	Async Ollama-grounded synthesis (phi3:mini) + real regulatory text
Optimiser	AdamW
Training framework	Docker container (Python 3.11, isolated from host)

---

Intended Use

Detecting prohibited practices including social scoring, real-time biometric surveillance in public spaces, subliminal manipulation, and emotion recognition in workplace/education contexts. Augments KlarKI's 9-pattern regex detection at confidence >= 0.85.

This model is a decision-support tool, not a substitute for qualified legal advice. EU AI Act compliance determinations should always be reviewed by a legal professional.

---

Limitations

• High-stakes classification — always used with deterministic pattern fallback in KlarKI.
• Context-dependent: the same phrase may or may not be prohibited depending on deployment setting.
• Do not use standalone for compliance decisions; use within an ensemble.

---

Citation

@software{klarki2026,
  author    = {Sankar},
  title     = {KlarKI: Local-First EU AI Act and GDPR Compliance Auditor},
  year      = {2026},
  url       = {https://github.com/s4nkar/KlarKI-EU-AI-Act-compliance-auditor},
  note      = {Open-source compliance tooling for German SMEs}
}

---

About KlarKI

KlarKI is an open-source, local-first EU AI Act + GDPR compliance auditor built for German SMEs. Upload a policy document and receive a scored gap analysis against Articles 9–15 entirely on your own hardware.

Key features:

• Deterministic legal decision hierarchy (actor detection, Annex III applicability gate)
• Hybrid RAG retrieval (BM25 + ChromaDB vector + cross-encoder re-ranking)
• LangGraph multi-agent gap analysis (3-node per applicable article)
• Bilingual EN/DE support — all inference runs locally, no external API calls

GitHub  |  All KlarKI Models