@inproceedings{li-etal-2025-revisiting-self,
    title = "Revisiting Self-Consistency from Dynamic Distributional Alignment Perspective on Answer Aggregation",
    author = "Li, Yiwei  and
      Zhang, Ji  and
      Feng, Shaoxiong  and
      Yuan, Peiwen  and
      Wang, Xinglin  and
      Shi, Jiayi  and
      Zhang, Yueqi  and
      Tan, Chuyi  and
      Pan, Boyuan  and
      Hu, Yao  and
      Li, Kan",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/2025.findings-acl.1293/",
    pages = "25208--25223",
    ISBN = "979-8-89176-256-5",
    abstract = "Self-consistency improves reasoning by aggregating diverse stochastic samples, yet the dynamics behind its efficacy remain underexplored. We reframe self-consistency as a dynamic distributional alignment problem, revealing that decoding temperature not only governs sampling randomness but also actively shapes the latent answer distribution. Given that high temperatures require prohibitively large sample sizes to stabilize, while low temperatures risk amplifying biases, we propose a confidence-driven mechanism that dynamically calibrates temperature: sharpening the sampling distribution under uncertainty to align with high-probability modes, and promoting exploration when confidence is high. Experiments on mathematical reasoning tasks show this approach outperforms fixed-diversity baselines under limited samples, improving both average and best-case performance across varying initial temperatures without additional data or modules. This establishes self-consistency as a synchronization challenge between sampling dynamics and evolving answer distributions."
}