@inproceedings{kim-etal-2026-reliability,
    title = "Reliability-Aware Adaptive Self-Consistency for Efficient Sampling in {LLM} Reasoning",
    author = "Kim, Junseok  and
      Yang, Nakyeong  and
      Min, Kyungmin  and
      Jung, Kyomin",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings 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.findings-acl.1085/",
    pages = "21575--21590",
    ISBN = "979-8-89176-395-1",
    abstract = "Self-Consistency improves reasoning reliability through multi-sample aggregation, but incurs substantial inference cost. Adaptive self-consistency methods mitigate this issue by adjusting the sampling budget; however, they rely on count-based stopping rules that treat all responses equally, often leading to unnecessary sampling. We propose \textbf{Re}liability-Aware \textbf{A}daptive \textbf{S}elf-\textbf{C}onsistency (), which addresses this limitation by reframing adaptive sampling from response counting to evidence sufficiency, leveraging response-level confidence for principled information aggregation. operates in two stages: a single-sample decision stage that resolves instances confidently answerable from a single response, and a reliability-aware accumulation stage that aggregates responses by jointly leveraging their frequency and confidence. Across five models and four datasets, consistently achieves the best accuracy-cost trade-off compared to existing baselines, yielding improved inference efficiency across model scales from 3B to 27B parameters. As a concrete example, reduces inference cost by up to 70{\%} relative to self-consistency while preserving accuracy on GSM8K using Gemma-3-4B-it."
}