method · first seen 6 Oct 2026
self-consistency
Also: self-consistency decoding, majority voting over samples, test-time scaling by majority voting, majority voting over sampled reasoning paths
Sampling multiple reasoning chains and taking a majority vote over final answers to improve accuracy.
Mentions per week
PapersCodeDiscussion
Earliest sources
- How Well Do LLMs Reason with Noisy Evidence? An Active Visual Reasoning BenchmarkPapers · 6 Oct 2026 · Bach Nguyen, Zhaonan Li, Mau Son Nguyen, Sanika Chavan, Nilay Kumar, Hong Anh Ng…
- ACED: Reference-Anchored Aggregation of Natural-Language and Executable Evidence for Mathematical ReasoningPapers · 12 Oct 2026 · Yiyi Lu, Jiaxiang Geng, Bing Luo
- Beyond Answer Voting: Fine-Grained Correction of LLM Reasoning through Graph Alignment across Sampled TracesPapers · 13 Oct 2026 · Haotian Liu, Yingjian Chen, Xiaohang Xu, Lang Huang, Yusuke Iwasawa, Yutaka Mats…
- From Unreliable to Usable: Decomposing Failure Modes and Confidence Signals in LLM Entity Extraction - Evidence from Cyber Threat IntelligencePapers · 14 Oct 2026 · Jiahong Qian
- When Judges Agree and Are Wrong: Consistency-Accuracy Dissociation as a Blind Spot for Label-Free EvaluationPapers · 15 Oct 2026 · Xiang Zhang, Lovedeep Gondara, Jekaterina Novikova
- Which Answers Agree? Evaluating Self-Consistency from Incomplete LogsPapers · 19 Oct 2026 · Zhengtao Gui, Zexi Chen, Weining Shen
Latest sources
- Anytime-Valid PAC-Bayes Certificates for Adaptive Test-Time ScalingPapers · 16 Nov 2026 · Xiaoyu Li, Jiangxuan Long
- When Is Proof-Step Verification Worth Its Cost? Operating Requirements of Certify-or-Decline Verification for Open-Weight Mathematical ReasoningPapers · 10 Nov 2026 · Abhinav Gupta, Ben Slivinski, Yashica Patodia, Michael Saldivar
- BARS: Budget-Aware Sequential Sampling with Refusal for Majority Identification under Unknown DistributionsPapers · 10 Nov 2026 · Shenxi Liu, Yiwei Li, Mingyang Zhao, Yuhang Tian, Kan Li
- When Self-Consistency Hurts: The Hidden Cost of Majority Voting in Small Language ModelsPapers · 8 Nov 2026 · Wanrong Yang, Lingfang Li, Jun Zhang, Dominik Wojtczak
- StepBack: Step-Level Error-Localized Resampling for Efficient Test-Time ReasoningPapers · 5 Nov 2026 · Yang Ouyang, Jung-Eun Kim
- Verifier-Guided Self-Consistency: Test-Time Reasoning with Imperfect Generators and VerifiersPapers · 4 Nov 2026 · Ekaterina Fadeeva, Xueyan Li, Mrinmaya Sachan, Maxim Panov
- Test-Time Scaling for Open-Ended Reasoning at Small Model ScalePapers · 1 Nov 2026 · Adam Y. Ahmed, Abdullah G. Elafifi
- CogRSI: Evolving and Auditing Cognitive Reasoning StrategiesPapers · 31 Oct 2026 · Yandan zheng, Haoran Luo, Xinliang Zhou, Anhtuan Luu
- Rethinking Neural Thickets Without Weight PerturbationsPapers · 29 Oct 2026 · Nicolas Dufour, Elouan Gardès, Amil Dravid, Patrick Pérez, Loic Landrieu
- Is Token Confidence Just Chain Length? A Signal-Processing Audit of Reasoning TracesPapers · 27 Oct 2026 · Pragna Mallappa
- Scaling Qualitative Analysis with Large Language Models: Development and Validation of the Smart Coder Framework for Human-LLM Collaborative CodingPapers · 23 Oct 2026 · Cheng Tang, Kun Wang, Yaxuan Yang, Shiyu Wang, Allan Cohen, Rachael Eriksen Brow…
- Which Answers Agree? Evaluating Self-Consistency from Incomplete LogsPapers · 19 Oct 2026 · Zhengtao Gui, Zexi Chen, Weining Shen