Baszta: Data-Centric Fine-Tuning of a Polish Multi-Label Safety Classifier

arXiv:2609.29266 · cs.AI · Submitted 2026-09-24 · Read on arXiv

cs.AI

Submitted: 2026-09-24

Updated: 2026-09-24

Terminology

• Calibration — 74× in this paper · explained in 7 episodes
• Benchmark — 68× in this paper · explained in 2 episodes
• Ablation — 14× in this paper · explained in 1 episode
• Robustness — 13× in this paper · explained in 5 episodes
• alpha — 12× in this paper · explained in 1 episode
• Accuracy — 10× in this paper · explained in 1 episode
• AUC — 7× in this paper · explained in 2 episodes
• Domain Shift — 6× in this paper · explained in 4 episodes
• Selection Bias — 4× in this paper · explained in 4 episodes
• Consistency — 3× in this paper · explained in 3 episodes
• Fine-Tuning — 3× in this paper · explained in 5 episodes
• Transformer — 3× in this paper · explained in 2 episodes
• Adaptation — 2× in this paper · explained in 1 episode
• Alignment — 2× in this paper · explained in 1 episode
• Provenance — 2× in this paper · explained in 4 episodes
• Tokenization — 2× in this paper · explained in 2 episodes
• Adam — 1× in this paper · explained in 2 episodes
• Adversarial Attacks — 1× in this paper · explained in 1 episode
• Adversarial Examples — 1× in this paper · explained in 2 episodes
• Adversarial Robustness — 1× in this paper · explained in 3 episodes
• Annotator Agreement — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 4 episodes
• Distillation — 1× in this paper · explained in 2 episodes
• Distribution Matching — 1× in this paper · explained in 2 episodes

Sources

• Bielik Guard: Efficient Polish Language Safety Classifiers for LLM Content Moderation
• Multilingual Refusal Alignment for Safer Large Language Models
• Detection of Criminal Texts for the Polish State Border Guard
• Universal and Transferable Adversarial Attacks on Aligned Language Models
• PolyGuard: A Multilingual Safety Moderation Tool for 17 Languages
• The Llama 3 Herd of Models
• Qwen3Guard Technical Report

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection