@inproceedings{dutulescu-etal-2026-orso,
    title = "{ORSO} {QG}en: Odds-Ratio Steerable Optimization for Controlling Question Generation",
    author = "Dutulescu, Andreea  and
      Ruseti, Stefan  and
      Dascalu, Mihai  and
      McNamara, Danielle S.",
    editor = "Demberg, Vera  and
      Inui, Kentaro  and
      Marquez, Llu{\'i}s",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EACL} 2026",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-swisstext/2026.findings-eacl.277/",
    doi = "10.18653/v1/2026.findings-eacl.277",
    pages = "5248--5259",
    ISBN = "979-8-89176-386-9",
    abstract = "Question generation plays an important role in educational applications, enabling automated assessment and reading comprehension support. Attribute-controlled question generation aims to produce questions that fit predefined characteristics such as difficulty, focus, or coverage. Existing methods predominantly rely on supervised fine-tuning, which often fails to impose a strong adherence to attribute values, resulting in weak coupling between prompt specifications and model outputs. We introduce Odds-Ratio Steerable Optimization (ORSO), a framework designed to enhance attribute sensitivity in question generation models. Building upon preference-based learning techniques without requiring human-curated preference sets, ORSO employs input-level perturbations to create contrastive training signals. Empirical evaluations on both exhaustive and expert-validated attribute configurations indicate that ORSO performs better in enforcing attribute conformity while maintaining output quality. These results argue for the benefits of explicit attribute-aware optimization in controllable question generation tasks."
}