Self-Consistency Decoding

Follow this topic Ask about this topic

Self-consistency decoding studies whether a model can give more reliable answers by generating several responses and combining them, often by majority vote over chain-of-thought reasoning. Methods also cluster semantically similar answers, rank candidates using trace or confidence signals, or use verification, adaptive sampling, and early stopping to spend compute more selectively. Evaluations span math and science reasoning, question answering, coding, information extraction, and multimodal tasks, with gains that vary by model, task, and decoding budget. A central tension is that more samples can help find correct answers but correlated errors and weak selection can limit or reverse those gains, so fair comparisons must account for compute and stronger alternatives such as input variation or verification.

Latest papers

33 papers2 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Diversity Combining for Multi-Path LLM Reasoning
Sep 30, 2026Guangsheng Yu, Litianyi Zhang, Qin Wang +5Inference-Time Optimization Self-Consistency Decoding
University of Technology Sydney · The University of Sydney · CSIRO +2
Learning via Self-Consistency for Diffusion-based Video Reasoning
Sep 29, 2026Zhenghao Ni, Weimin Qiu, Meng TangVideo Diffusion Models Self-Consistency Decoding
University of Toronto · University of California, Merced
The Detectability Gap: Hidden Heterogeneity in Hallucination Detection Across Language Models
Sep 25, 2026Pranav Darshan, Pranav A, Sravan Karthick T +2Factual QA Hallucination Detection
Department of Computer Science and Engineering, R.V. College of Engineering, India · CAIRO, Technical University of Applied Sciences Würzburg-Schweinfurt, Germany
Test-Time Augmentation for LLMs: Where to Inject Diversity at Inference Time
Aug 10, 2026Nikita Kozodoi, Zainab Afolabi, Jack ButlerLLM Inference Efficiency Self-Consistency Decoding
Amazon Web Services
When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs
Aug 4, 2026Omatharv Bharat Vaidya, Connor Thomas Jerzak, Zayne Rea Sprague +2Self-Consistency Decoding Symbolic Reasoning
The University of Texas at Austin · New York University
It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling
Aug 2, 2026Puzhuo Zheng, Hasan KurbanVLM Evaluation Self-Consistency Decoding
College of Science and Engineering, Hamad Bin Khalifa University, Doha, Qatar
Sample More, Reflect Less: Self-Refine and Reflexion Lose to Repeated Sampling at Equal Token Cost, from 1.5B to 7B
Jul 30, 2026Iliya MirzaeiLanguage Model Self-Assessment LLM Self-Refinement
Department of Computer Science Stony Brook University
How far do on-premises open LLMs get on Text-to-SQL? A cross-family size and technique frontier on BIRD
Jun 29, 2026Vladimir BeskorovainyiLLM Self-Correction LLM Evaluation
Besk Tech | Moscow Institute of Physics and Technology (MIPT)
When More Sampling Hurts: The Modal Ceiling and Correlation Ceiling of Test-Time Scaling
Jun 27, 2026Yong Yi Bay, Kathleen A. YearickLLM Evaluation Self-Consistency Decoding
University of Illinois at Urbana-Champaign
SFL-MTSC: Leveraging Semantic Frame-Level Multi-Task Self-Consistency for Robust Multi-Intent Spoken Language Understanding
Jun 24, 2026Po-Yen Chen, Berlin ChenSpoken Language Understanding Self-Consistency Decoding
National Taiwan Normal University, Taiwan
A Self Consistency Based Reranking for Narrative Question Answering
Jun 14, 2026Molham Mohamed, Ali HamdiSelf-Consistency Decoding Question Answering
Faculty of Computer Science MSA University Giza, Egypt
MARS: Margin-Adversarial Risk-controlled Stopping for Parallel LLM Test-time Scaling
Jun 11, 2026Wenbo Chen, Puheng Li, Mengyang Liu +2LLM Inference Efficiency Self-Consistency Decoding
Amazon · Stanford University · University of Pennsylvania
Agreement in Representation Space for Open-Ended Self-Consistency
Jun 10, 2026Paula Ontalvilla, Gorka Azkune, Aitor OrmazabalOpen-Ended Generation Self-Consistency Decoding
HiTZ Center - Ixa, University of the Basque Country (UPV/EHU)
A Pre-Registered Causal Partition of Self-Consistency Elicitation and Reward Design in RLVR
Jun 4, 2026Yuze GaoReinforcement Learning Self-Consistency Decoding
Boosting Self-Consistency with Ranking
Jun 3, 2026Maria Marina, Daniil Moskovskiy, Sergey Pletenev +3Self-Consistency Decoding LLM Reranking
AIRI · Skoltech · EPFL
Answer Self-Consistency with Margin-Triggered Question Re-Arbitration for the CVPR 2026 VidLLMs Challenge
Jun 3, 2026Tomoya Miyazawa, Hiroyasu OkunoVLM Evaluation Self-Consistency Decoding
Data Analytics Labo Co.
KACE: Knowledge-Adaptive Context Engineering for Mathematical Reasoning
May 30, 2026Jayant Parashar, Suchendra M. BhandarkarMemory-Augmented Language Models Self-Consistency Decoding
School of Computing, University of Georgia
ARBITER: Reasoning Trajectory Basins and Majority Vote Failures in Test-Time Sampling
May 25, 2026Meng Cai, Lars Kulik, Farhana ChoudhurySelf-Consistency Decoding Test-Time Scaling
School of Computing and Information Systems University of Melbourne
Pause and Reflect: Conformal Aggregation for Chain-of-Thought Reasoning
May 13, 2026Yu Gu, Zijun Yu, Vahid Partovi Nia +1Selective Prediction Self-Consistency Decoding
Department of Mathematics and Statistics McGill University Montréal, QC, Canada · Department of Mathematics and Industrial Engineering Polytechnique de Montréal Montréal, QC, Canada
Edit-level Majority Voting Mitigates Over-Correction in LLM-based Grammatical Error Correction
May 13, 2026Takumi Goto, Yusuke Sakai, Taro WatanabeSelf-Consistency Decoding Grammatical Error Correction
Nara Institute of Science and Technology (NAIST)
Reliable Chain-of-Thought via Prefix Consistency
May 8, 2026Naoto Iwase, Yuki Ichihara, Mohammad Atif Quamar +1Self-Consistency Decoding Reasoning Consistency in Language Models
Nagoya University · Nara Institute of Science and Technology · Mohamed bin Zayed University of Artificial Intelligence +1
The First Token Knows: Single-Decode Confidence for Hallucination Detection
May 6, 2026Mina GabrielFactual QA Uncertainty Quantification
Department of Computer and Information Sciences Temple University Philadelphia, PA 19122, USA
Multi-Agent Reasoning Improves Compute Efficiency: Pareto-Optimal Test-Time Scaling
May 2, 2026Florian Valentin Wunderlich, Lars Benedikt Kaesberg, Jan Philip Wahle +2Self-Consistency Decoding Cost-Aware Inference
University of Göttingen, Germany
Distilling Self-Consistency into Verbal Confidence: A Pre-Registered Negative Result and Post-Hoc Rescue on Gemma 3 4B
Apr 27, 2026Jon-Paul CacioliSupervised Fine-Tuning Confidence Estimation in Language Models
Independent Researcher, Melbourne, Australia
Efficient Test-Time Inference via Deterministic Exploration of Truncated Decoding Trees
Apr 22, 2026Xueyan Li, Johannes Zenn, Ekaterina Fadeeva +3Language Model Decoding Inference-Time Search
Max Planck Institute for Intelligent Systems · ETH Zurich · AI Center Tübingen +3
Does Self-Consistency Improve the Recall of Encyclopedic Knowledge?
Apr 21, 2026Sho Hoshino, Ukyo Honda, Peinan ZhangSelf-Consistency Decoding CoT Reasoning
CyberAgent
Self-Consistency from Only Two Samples: CoT-PoT Ensembling for Efficient LLM Reasoning
Apr 19, 2026Raman Saparkhan, Majd Hawasly, Md Rizwan Parvez +1LLM Inference Efficiency Self-Consistency Decoding
Carnegie Mellon University Qatar · Qatar Computing Research Institute
Correct Prediction, Wrong Steps? Consensus Reasoning Knowledge Graph for Robust Chain-of-Thought Synthesis
Apr 15, 2026Zipeng Ling, Shuliang Liu, Seonil Son +4Reasoning Trace Analysis Logical Reasoning
The Hong Kong University of Science and Technology (Guangzhou) · University of Alberta · Alberta Machine Intelligence Institute +3
Self-Consistency for LLM-Based Motion Trajectory Generation and Verification
Mar 31, 2026Jiaju Ma, R. Kenny Jones, Jiajun Wu +1Trajectory Generation Self-Consistency Decoding
Stanford University
Model Capability Dominates: Inference-Time Optimization Lessons from AIMO 3
Mar 29, 2026Natapong NitarachLLM Reasoning LLM Prompting

Sep 30, 2026J/K move · Enter open · S save

Diversity Combining for Multi-Path LLM Reasoning

Guangsheng Yu, Litianyi Zhang, Qin Wang, Xu Wang+4

University of Technology Sydney · The University of Sydney · CSIRO+2

Inference-Time Optimization Self-Consistency Decoding Prompt Engineering Large Reasoning Models

Open paper AskPDF arXiv

Multi-path reasoning methods such as self-consistency (SC) sample

K

reasoning paths and choose the most frequent answer. However, their gains quickly plateau as

K

increases, and locating this saturation point currently requires fitting a scaling model to accuracies measured at several values of

K

or stopping online per query. We formalize multi-path LLM reasoning as a diversity combining problem from wireless communications: each path is a noisy channel observation, and the pairwise correlation of path correctness caps the design-effect effective sample size of the vote at a finite ceiling. Generalized least squares (GLS) analysis shows that, for paths with equal gains, the optimal linear combiner of latent embeddings is uniform exactly when every row of the path covariance has the same sum, as under exchangeability, supporting majority vote as the natural default in standard SC while leaving room for weighting or pruning under heterogeneous prompt-template branches. Across 5 models and 12 benchmarks, prompt-template diversity reduces path correlation in

55

60

model-benchmark cells, with a mean relative reduction of

16\%

and reductions in every task domain. We derive an Adaptive-K rule that uses a four-path pilot to select

K^*

, retaining

96

103\%

of MV@

K{=}32

accuracy across Math, QA, and NLU.