It is part of the MAHALO (Multi-Action-Head ALignment with PRM-guided DecOding) framework, which standardizes PRM training across verifiable and non-verifiable settings for step-level supervision. This specific model provides reward signals for the honesty dimension in open-domain conversations.

Repository: https://github.com/pearls-lab/multiobj-align
Paper: https://huggingface.co/papers/2510.01167

Model description

This model uses the LlamaForSequenceClassification architecture to evaluate the honesty of steps in a dialogue. It was trained as part of a multi-objective alignment setup to allow for controllable inference and improved human value alignment.

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 1e-05
train_batch_size: 4
eval_batch_size: 4
seed: 42
distributed_type: multi-GPU
num_devices: 8
gradient_accumulation_steps: 16
total_train_batch_size: 512
total_eval_batch_size: 32
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.03
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.3012	0.4632	50	0.2989	0.886
0.2851	0.9265	100	0.2657	0.908

Framework versions

Transformers 4.45.2
Pytorch 2.5.1+cu124
Datasets 3.1.0
Tokenizers 0.20.3

Citation

If you find this work useful, please cite:

bibtex

@article{shen2025simultaneous,
  title={Simultaneous Multi-objective Alignment Across Verifiable and Non-verifiable Rewards},
  author={Shen, Yiran and Xia, Yu and Chang, Jonathan and Ammanabrolu, Prithviraj},
  journal={arXiv preprint arXiv:2510.01167},
  year={2025},
  url={https://arxiv.org/abs/2510.01167}
}

Jennny/llama3_8b_honest_rm_full

llama3_8b_honest_rm_full