@inproceedings{yeom-etal-2026-epicar,
    title = "{E}pi{C}a{R}: Knowing What You Don{'}t Know Matters for Better Reasoning in {LLM}s",
    author = "Yeom, Jewon  and
      Sok, Jaewon  and
      Park, Seonghyeon  and
      Park, Jeongjae  and
      Kim, Taesup",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.1026/",
    pages = "22414--22443",
    ISBN = "979-8-89176-390-6",
    abstract = "Improving the reasoning abilities of large language models (LLMs) has largely relied on iterative self-training with model-generated data. While effective at boosting accuracy, existing approaches primarily reinforce successful reasoning paths, incurring a substantial calibration cost: models become overconfident and lose the ability to represent uncertainty. This failure has been characterized as a form of model collapse in alignment, where predictive distributions degenerate toward low-variance point estimates.We address this issue by reframing open-ended reasoning training as an epistemic learning problem, in which models must learn not only how to reason, but also when their reasoning should be trusted. We propose epistemically-calibrated reasoning (EpiCaR) as a training objective that jointly optimizes reasoning performance and calibration, and instantiate it within an iterative supervised fine-tuning framework using explicitly extracted meta-cognitive self-evaluation signals. Experiments on Llama-3 and Qwen-3 families demonstrate that our approach achieves Pareto-superiority over standard baselines in both accuracy and calibration, particularly in models with sufficient reasoning capacity (e.g., 3B+). This framework generalizes effectively to OOD mathematical reasoning (GSM8K) and code generation (MBPP). Ultimately, our approach enables a $3\times$ reduction in the overall inference compute budget, matching the $K=30$ majority-vote performance of STaR with only $K=10$ confidence-weighted samples, entirely without the multi-model overhead of external verifiers."
}