Author

Niclas Müller-Hof

h-index 1 View on Semantic Scholar

We have 1 of 2 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#natural language process... Jun 2026

Paved with True Intents: Intent-Aware Training Improves LLM Safety Classification Across Training Regimes

AIMS, a human-annotated dataset of 1,724 difficult safety prompts, is introduced to evaluate intent-aware training across supervised fine-tuning, preference learning, reasoning distillation, and reinforcement learning and shows that faithful intent modeling is a compact, high-quality supervision signal for more robust...

J. Ferrao, Niclas Müller-Hof, Iustin Sîrbu et al. · arXiv.org · 1 citation