THU-KEG/TULU3-VerIF

Model Card for Model ID

Model Details

Model Description

• Developed by: Hao Peng@THUGKEG
• Model type: RL trained LLMs
• Language(s) (NLP): English, Chinese
• License: apache-2.0
• Finetuned from model [optional]: allenai/Llama-3.1-Tulu-3-8B-SFT

Model Sources [optional]

• Repository: https://github.com/THU-KEG/VerIF
• Paper: https://arxiv.org/abs/2506.09942

Training Details

The model is trained using RL with VerIF, using train data VerInstruct.

VerIF is a practical and efficient method for verification in instruction-following reinforcement learning. Built on the idea of Reinforcement Learning with Verifiable Rewards (RLVR), VerIF integrates rule-based code checks with LLM-based reasoning verification (e.g., QwQ-32B) to provide accurate and scalable reward signals.

The model is optimized for instruction-following, without affecting other general capabilities.

Evaluation Results

We evaluate the model on several representative instruction-following benchmarks, including IFEval, Multi-IF, SysBench, FollowBench, and etc..

You can find more details in our github repo (https://github.com/THU-KEG/VerIF). If you find this model helpful, please kindly cite us:

@misc{peng2025verif,
      title={VerIF: Verification Engineering for Reinforcement Learning in Instruction Following}, 
      author={Hao Peng and Yunjia Qi and Xiaozhi Wang and Bin Xu and Lei Hou and Juanzi Li},
      year={2025},
      eprint={2506.09942},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2506.09942}, 
}