TARS-1.5B

Overview

TARS-1.5B is an open-source reasoning model trained for safety using TARS: Training Adaptive Reasoners for Safety introduced in the paper: Reasoning as an Adaptive Defense for Safety, to facilitate the research of reasoning models for LLM safety. This model is trained using a mixing ratio of $\lambda =0.5\backslash lambda\; =\; 0.5$ between harmful and harmless prompts, starting from the base model Qwen2.5-1.5B-Instruct.

TARS is a simple but effective online reinforcement learning (RL) method that trains models to adaptively reason for low refusal and safe behavior, using three key ingredients:

🔑 Key Ingredients

• Ingredient 1: Lightweight supervised fine-tuning (SFT) for diverse generations
• Ingredient 2: Mixing in harmless prompts during RL training
• Ingredient 3: Decoupled reward model for better exploration

For full details, please check out our paper or blogpost.

---

📖 Citation

If you use TARS-1.5B in your work, please cite us:

@misc{kim2025reasoningadaptivedefensesafety,
  title        = {Reasoning as an Adaptive Defense for Safety},
  author       = {Taeyoun Kim and Fahim Tajwar and Aditi Raghunathan and Aviral Kumar},
  year         = {2025},
  eprint       = {2507.00971},
  archivePrefix= {arXiv},
  primaryClass = {cs.LG},
  url          = {https://arxiv.org/abs/2507.00971}
}