@inproceedings{bystronski-etal-2026-continuous,
    title = "Continuous Context Sampling Allows Extending Diversity Boundaries of Large Language Models",
    author = "Bystro{\'n}ski, Mateusz  and
      Han, Doheon  and
      Chawla, Nitesh V.  and
      Kajdanowicz, Tomasz Jan",
    editor = "T.Y.S.S., Santosh  and
      Rodriguez, Juan Diego  and
      de Gibert, Ona",
    booktitle = "Proceedings of the 64th Annual Meeting 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.acl-srw.126/",
    pages = "1436--1450",
    ISBN = "979-8-89176-393-7",
    abstract = "Starting from the observation that conditioning a poetry-writing prompt with a pancake recipe leads an LLM to produce a coherent poem incorporating pancake-related content and, more broadly, that such contexts arrange themselves into a structured semantic vector space, we argue that this renders the space explorable. By sampling it and using the resulting continuous representations to condition an LLM{'}s generation distribution, we can systematically expand the model{'}s reachable semantic range.We introduce a framework that requires no modification of LLM parameters and operationalizes this idea by constructing a conditioning distribution from a small set of diverse anchor generations. This distribution conditions LLM{'}s generation via an xRAG-style projector.Our experiments demonstrate that this manifold-based conditioning substantially increases generative diversity, with direct benefits for enhancing divergent thinking, a core facet of creativity, in language models."
}