Lune

ACL Findings2026

PiCSAR: Probabilistic Confidence Selection and Ranking for Reasoning Chains

Joshua Ong Jun Leang, Zheng Zhao, Aryo Pradipta Gema, Sohee Yang, Wai-Chung Kwan, Xuanli He, Wenda Li, Pasquale Minervini, Eleonora Giunchiglia, Shay B. Cohen

Abstract

Best-of-n sampling improves the accuracy of large language models (LLMs) and large reasoning models (LRMs) by generating multiple candidate solutions and selecting the one with the highest reward. A key challenge for reasoning tasks is designing a scoring function that can identify correct reasoning chains without access to ground-truth answers. We propose Probabilistic Confidence Selection And Ranking (PiCSAR): a simple, trainingfree method that scores each candidate generation using the joint log-likelihood of the reasoning and final answer. This method uses both the scores of the reasoning path (reasoning confidence) and the final answer (answer confidence). PiCSAR achieves substantial gains across several benchmarks (+11.7 on AIME2024, +9.81 on AIME2025), outperforming baselines with at least 2x fewer samples in 20 out of 25 comparisons. Our analysis reveals that correct reasoning chains exhibit higher reasoning and answer confidence levels, justifying the effectiveness of PiCSAR 1 .

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.

2 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Tree of Thoughts: Deliberate Problem Solving with Large Language Models cites Self-Refine: Iterative Refinement with Self-Feedback
  • Tree of Thoughts: Deliberate Problem Solving with Large Language Models cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
  • Self-Refine: Iterative Refinement with Self-Feedback cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
  • Large Language Models are Zero-Shot Reasoners cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
  • Let's Verify Step by Step cites Large Language Models are Zero-Shot Reasoners
  • Let's Verify Step by Step cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
  • Uncertainty Quantification in LLM Agents: Foundations, Emerging Challenges, and Opportunities cites Self-Refine: Iterative Refinement with Self-Feedback
  • Uncertainty Quantification in LLM Agents: Foundations, Emerging Challenges, and Opportunities cites Let's Verify Step by Step
  • Uncertainty Quantification in LLM Agents: Foundations, Emerging Challenges, and Opportunities cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
  • LogicReward: Incentivizing LLM Reasoning via Step-Wise Logical Supervision cites Tree of Thoughts: Deliberate Problem Solving with Large Language Models
  • LogicReward: Incentivizing LLM Reasoning via Step-Wise Logical Supervision cites Let's Verify Step by Step
  • LogicReward: Incentivizing LLM Reasoning via Step-Wise Logical Supervision cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers2

  1. LogicReward: Incentivizing LLM Reasoning via Step-Wise Logical SupervisionJundong Xu, Hao (Scofield) Fei, Huichi Zhou, Xin Quan et al.ICLR 2026 · 9 citations
  2. Uncertainty Quantification in LLM Agents: Foundations, Emerging Challenges, and OpportunitiesChangdae Oh, Seongheon Park, To Eun Kim, Jiatong Li et al.ACL 2026 · 8 citations

Builds on26

  1. Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsJason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma et al.NeurIPS 2022 · 22,562 citations
  2. Large Language Models are Zero-Shot ReasonersTakeshi Kojima, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo et al.NeurIPS 2022 · 8,168 citations
  3. Tree of Thoughts: Deliberate Problem Solving with Large Language ModelsShunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran et al.NeurIPS 2023 · 5,068 citations
  4. Self-Refine: Iterative Refinement with Self-FeedbackAman Madaan, Niket Tandon, Prakhar Gupta, Skyler Hallinan et al.NeurIPS 2023 · 4,972 citations
  5. Let's Verify Step by StepHunter Lightman, Vineet Kosaraju, Yuri Burda, Harrison Edwards et al.ICLR 2024 · 3,045 citations

Related papers

  1. Scalable Best-of-N Selection for Large Language Models via Self-CertaintyZhewei Kang, Xuandong Zhao, Dawn SongNeurIPS 2025 · 211 citations
  2. Sample Smart, Not Hard: Correctness-First Decoding for Better Reasoning in LLMsXueyan Li, Guinan Su, Mrinmaya Sachan, Jonas GeipingICLR 2026 · 5 citations
  3. Beyond Binary Rewards: Training LMs to Reason About Their UncertaintyMehul Damani, Isha Puri, Stewart Slocum, Idan Shenfeld et al.ICLR 2026 · 116 citations
  4. Selection-Inference: Exploiting Large Language Models for Interpretable Logical ReasoningAntonia Creswell, Murray Shanahan, Irina HigginsICLR 2023 · 110 citations
  5. Self-Training Large Language Models with Confident ReasoningHyosoon Jang, Yunhui Jang, Sungjae Lee, Jungseul Ok et al.EMNLP Findings 2025 · 1 citation
Dusk over the sea between two cliffs drawn in fine vertical lines