@inproceedings{botcazou-etal-2026-progress,
    title = "Progress Ratio Embeddings: An Impatience Signal for Robust Length Control in Neural Text Generation",
    author = "Botcazou, Ivanho{\textbackslash}'e  and
      Amghar, Tassadit  and
      Lamprier, Sylvain  and
      Saubion, Fr{\textbackslash}'ed{\textbackslash}'eric",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.286/",
    pages = "5776--5789",
    ISBN = "979-8-89176-395-1",
    abstract = "Modern neural language models achieve high accuracy in text generation, yet precise control over generation length remains underdeveloped. In this paper, we first investigate a recent length control method based on Reverse Positional Embeddings (RPE) and show its limits when control is requested beyond the training distribution. In particular, using a discrete countdown signal tied to the absolute remaining token count leads to instability. To provide robust length control, we introduce Progress Ratio Embeddings (PRE), as continuous embeddings tied to a trigonometric impatience signal. PRE integrates seamlessly into standard Transformer architectures, providing stable length fidelity without degrading text accuracy under standard evaluation metrics. We further show that PRE generalizes well to unseen target lengths. Experiments on two widely used news-summarization benchmarks and a popular question generation dataset validate these findings."
}