@inproceedings{deshpande-etal-2025-diverse,
    title = "Diverse, not Short: A Length-Controlled Data Selection Strategy for Improving Response Diversity of Language Models",
    author = "Deshpande, Vijeta  and
      Ghose, Debasmita  and
      Patterson, John D  and
      Beaty, Roger E.  and
      Rumshisky, Anna",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.emnlp-main.1721/",
    doi = "10.18653/v1/2025.emnlp-main.1721",
    pages = "33905--33926",
    ISBN = "979-8-89176-332-6",
    abstract = "Diverse language model responses are crucial for creative generation, open-ended tasks, and self-improvement training. We show that common diversity metrics, and even reward models used for preference optimization, systematically bias models toward shorter outputs, limiting expressiveness. To address this, we introduce Diverse, not Short (Diverse-NS), a length-controlled data selection strategy that improves response diversity while maintaining length parity. By generating and filtering preference data that balances diversity, quality, and length, Diverse-NS enables effective training using only 3,000 preference pairs. Applied to LLaMA-3.1-8B and the Olmo-2 family, Diverse-NS substantially enhances lexical and semantic diversity. We show consistent improvement in diversity with minor reduction or gains in response quality on four creative generation tasks: Divergent Associations, Persona Generation, Alternate Uses, and Creative Writing. Surprisingly, experiments with the Olmo-2 model family (7B, and 13B) show that smaller models like Olmo-2-7B can serve as effective ``diversity teachers'' for larger models. By explicitly addressing length bias, our method efficiently pushes models toward more diverse and expressive outputs."
}