Lune

ACL Findings2026

Reliability-Aware Adaptive Self-Consistency for Efficient Sampling in LLM Reasoning

Junseok Kim, Nakyeong Yang, Kyungmin Min, Kyomin Jung

Abstract

Self-Consistency improves reasoning reliability through multi-sample aggregation, but incurs substantial inference cost. Adaptive selfconsistency 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 Reliability-Aware Adaptive Self-Consistency (ReASC), which addresses this limitation by reframing adaptive sampling from response counting to evidence sufficiency, leveraging response-level confidence for principled information aggregation. ReASC 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, ReASC 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, ReASC reduces inference cost by up to 70% relative to self-consistency while preserving accuracy on GSM8K using Gemma-3-4B-it.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Scalable Best-of-N Selection for Large Language Models via Self-Certainty cites Self-Consistency Improves Chain of Thought Reasoning in Language Models
  • Scalable Best-of-N Selection for Large Language Models via Self-Certainty cites Let's Verify Step by Step
  • Let's Verify Step by Step cites Self-Consistency Improves Chain of Thought Reasoning in Language Models
  • Chain-of-Thought Reasoning Without Prompting cites Self-Consistency Improves Chain of Thought Reasoning in Language Models
  • Chain-of-Thought Reasoning Without Prompting cites Let's Verify Step by Step
  • Deep Think with Confidence cites Scalable Best-of-N Selection for Large Language Models via Self-Certainty
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on9

  1. Let's Verify Step by StepHunter Lightman, Vineet Kosaraju, Yuri Burda, Harrison Edwards et al.ICLR 2024 · 3,045 citations
  2. Self-Consistency Improves Chain of Thought Reasoning in Language ModelsXuezhi Wang, Jason Wei, Dale Schuurmans, Quoc V. Le et al.ICLR 2023 · 681 citations
  3. Chain-of-Thought Reasoning Without PromptingXuezhi Wang, Denny ZhouNeurIPS 2024 · 305 citations
  4. Scalable Best-of-N Selection for Large Language Models via Self-CertaintyZhewei Kang, Xuandong Zhao, Dawn SongNeurIPS 2025 · 211 citations
  5. Deep Think with ConfidenceYichao Fu, Xuewei Wang, Hao Zhang, Yuandong Tian et al.ICLR 2026 · 171 citations

Related papers

  1. Let's Sample Step by Step: Adaptive-Consistency for Efficient Reasoning and Coding with LLMsPranjal Aggarwal, Aman Madaan, Yiming Yang, MausamEMNLP 2023 · 5 citations
  2. Task-and-Model-Aware Fractal-Consistency for Efficient LLM ReasoningZiqiu Luo, Jianmin Liu, Yukai Miao, Li Chen et al.ICML 2026
  3. Optimal Self-Consistency for Efficient Reasoning with Large Language ModelsAustin Feng, Marius Alonso, Ambroise Odonnat, Vasilii Feofanov et al.ICML 2026 · 6 citations
  4. Optimal Bayesian Stopping for Efficient Inference of Consistent LLM AnswersJingkai Huang, Will Ma, Zhengyuan ZhouICML 2026 · 3 citations
  5. THE PATH OF LEAST RESISTANCE: GUIDING LLM REASONING TRAJECTORIES WITH PREFIX CONSENSUSIshan Jindal, Sai Prashanth Akuthota, Jayant Taneja, Sachin Dev SharmaICLR 2026 · 1 citation
Dusk over the sea between two cliffs drawn in fine vertical lines