EdyVision/praxa-behavioral-modernbert-base

Praxa behavioral encoder comparator (ModernBERT-base)

Published ModernBERT-base fine-tune used as the long-context encoder comparator in the RFDT / behavioral policy adaptation study.

Base model: answerdotai/ModernBERT-base

Eval metrics live in EdyVision/praxa-behavioral-experiments.

Associated paper

Rosado, E. J. (2026). RFDT: Representation-first decision training for behavioral policy adaptation [Preprint]. URL pending.

Acknowledgments and attribution

COMPASS dataset

Thanks to the COMPASS authors for the organization-specific policy alignment testbed used by this study.

Choi, D., Lee, D., Kartono, B. J., Berndt, H., Kwon, T., Jang, J., Park, H., Yu, H., & Kahng, M. (2026). COMPASS: A framework for evaluating organization-specific policy alignment in LLMs (arXiv:2601.01836). arXiv. https://arxiv.org/abs/2601.01836

Upstream dataset: AIM-Intelligence/COMPASS-Policy-Alignment-Testbed-Dataset.

Foundation models

Thanks to the ModernBERT authors for the encoder used in this comparator:

Warner, B., Chaffin, A., Clavié, B., Weller, O., Hallström, O., Taghadouini, S., Gallagher, A., Biswas, R., Ladhak, F., Aarsen, T., Cooper, N., Adams, G., Howard, J., & Poli, I. (2024). Smarter, better, faster, longer: A modern bidirectional encoder for fast, memory efficient, and long context finetuning and inference (arXiv:2412.13663). arXiv. https://arxiv.org/abs/2412.13663

Matched-primary companion models in this study:

• Yang, A., et al. (2025). Qwen3 technical report (arXiv:2505.09388). arXiv. https://arxiv.org/abs/2505.09388
• IBM Research. (2026). Granite 4.1 language models. https://huggingface.co/blog/ibm-granite/granite-4-1
• Liu, A. H., et al. (2026). Ministral 3 (arXiv:2601.08584). arXiv. https://arxiv.org/abs/2601.08584

How to cite

Rosado, E. J. (2026). RFDT: Representation-first decision training for behavioral policy adaptation [Preprint]. URL pending.

Also cite Choi et al. (2026) for COMPASS and Warner et al. (2024) for ModernBERT.