gelatwo-common-gen-gpt2-large

gpt2-large fine-tuned on CommonGen, used as the base language model for the CommonGen experiments in Mitigating Bias in Locally Constrained Decoding via Tractable Proposals (arXiv:2606.01926).

This is a plain causal language model: it supplies the base distribution that GCD and P-GCD steer. The tractable proposal it is paired with is the HMM at mhdang/gelatwo-common-gen-dense-4096, which shares its 50257-token vocabulary.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("mhdang/gelatwo-common-gen-gpt2-large")
tokenizer = AutoTokenizer.from_pretrained("openai-community/gpt2-large")

configs/common-gen.yaml in github.com/MhDang/gelatwo already points at this checkpoint, so the CommonGen runs need no override.

Citation

@inproceedings{dang2026mitigating,
  title = {Mitigating Bias in Locally Constrained Decoding via Tractable Proposals},
  author = {Dang, Meihua and Song, Linxin and Zhang, Honghua and Zhao, Jieyu and Van den Broeck, Guy and Ermon, Stefano},
  booktitle = {Proceedings of the 43rd International Conference on Machine Learning (ICML)},
  year = {2026},
}