@inproceedings{zhang-etal-2026-confidence,
    title = "Confidence-Calibrated Small-Large Language Model Collaboration for Cost-Efficient Reasoning",
    author = "Zhang, Chuang  and
      Zhu, Zizhen  and
      Wei, Yihao  and
      Tian, Bing  and
      Liu, Junyi  and
      Wang, Henan  and
      Xavier, Wang  and
      Liu, Yaxiao",
    editor = "Demberg, Vera  and
      Inui, Kentaro  and
      Marquez, Llu{\'i}s",
    booktitle = "Proceedings of the 19th Conference of the {E}uropean Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-eacl/2026.eacl-long.208/",
    pages = "4480--4501",
    ISBN = "979-8-89176-380-7",
    abstract = "Large language models (LLMs) demonstrate superior reasoning capabilities compared to small language models (SLMs), but incur substantially higher costs. We propose COllaborative REAsoner (COREA), a system that cascades an SLM with an LLM to achieve a balance between accuracy and cost in complex reasoning tasks. COREA first attempts to answer questions using the SLM, which outputs both an answer and a verbalized confidence score. Questions with confidence below a predefined threshold are deferred to the LLM for more accurate resolution. We introduce a reinforcement learning-based training algorithm that aligns the SLM{'}s confidence through an additional confidence calibration reward. Extensive experiments demonstrate that our method jointly improves the SLM{'}s reasoning ability and confidence calibration across diverse datasets and model backbones. Compared to using the LLM alone, COREA reduces cost by 21.5{\%} and 16.8{\%} on out-of-domain math and non-math datasets, respectively, with only an absolute pass@1 drop within 2{\%}."
}