Paved with True Intents: Intent-Aware Training Improves LLM Safety Classification Across Training Regimes
We argue that safety classifiers should model user intent as an explicit signal between the prompt and the final label. To study this, we introduce AIMS, a human-annotated dataset of 1,724 difficult safety prompts, each paired with an intent description and harm label. We use AIMS to evaluate intent-aware training across supervised fine-tuning, preference learning, reasoning distillation, and reinforcement learning. Despite its size, AIMS enables competitive safety classifiers across training regimes: DPO from model-generated intent errors improves over SFT, and intent-conditioned distillation outperforms reasoning-only distillation in most teacher-student pairs. Most notably, directly re...
| Authors | Jeremias Ferrao, Niclas Müller-Hof, Iustin Sîrbu et al. |
|---|---|
| Primary category | cs.CL |
| Published | 25 June 2026 |
| Last updated at source | 25 June 2026 |
Models and datasets referencing this paper
- Jazhyc/aims-safety-intentsDataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.