Copertina

Certified Self-Consistency: Statistical Guarantees and Test-Time Training for Reliable Reasoning in LLMs

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Cordero-Encinar, Paula, Duncan, Andrew B.
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Soft Specialists: $α$-Rényi Ensembles for Uncertainty-Aware LLM Post-Training
di: Cordero-Encinar, Paula, et al.
Pubblicazione: (2026)

Non-asymptotic Analysis of Diffusion Annealed Langevin Monte Carlo for Generative Modelling
di: Cordero-Encinar, Paula, et al.
Pubblicazione: (2025)

Deep Optimal Sensor Placement for Black Box Stochastic Simulations
di: Cordero-Encinar, Paula, et al.
Pubblicazione: (2024)

Sampling by averaging: A multiscale approach to score estimation
di: Cordero-Encinar, Paula, et al.
Pubblicazione: (2025)

Diffusion Path Samplers via Sequential Monte Carlo
di: Young, James Matthew, et al.
Pubblicazione: (2026)

Diffusion annealed Langevin dynamics: a theoretical study
di: Cattiaux, Patrick, et al.
Pubblicazione: (2025)

Proximal Interacting Particle Langevin Algorithms
di: Encinar, Paula Cordero, et al.
Pubblicazione: (2024)

Self-Training Meets Consistency: Improving LLMs' Reasoning with Consistency-Driven Rationale Evaluation
di: Lee, Jaehyeok, et al.
Pubblicazione: (2024)

Reliability-Aware Adaptive Self-Consistency for Efficient Sampling in LLM Reasoning
di: Kim, Junseok, et al.
Pubblicazione: (2026)

Reliable Statistical Guarantees for Conformal Predictors with Small Datasets
di: Sánchez-Domínguez, Miguel, et al.
Pubblicazione: (2025)

Round-trip Reinforcement Learning: Self-Consistent Training for Better Chemical LLMs
di: Kong, Lecheng, et al.
Pubblicazione: (2025)

Certainty in Uncertainty: Reasoning over Uncertain Knowledge Graphs with Statistical Guarantees
di: Zhu, Yuqicheng, et al.
Pubblicazione: (2025)

Causal Discovery for Irregularly Time Series with Consistency Guarantees
di: Li, Weihong, et al.
Pubblicazione: (2025)

$H$-Consistency Guarantees for Regression
di: Mao, Anqi, et al.
Pubblicazione: (2024)

LGMT: Logic-Grounded Metamorphic Testing for Evaluating the Reasoning Reliability of LLMs
di: Zhou, Zenghui, et al.
Pubblicazione: (2026)

Self-Trained Verification for Training- and Test-Time Self-Improvement
di: Wu, Chen Henry, et al.
Pubblicazione: (2026)

Ranking Reasoning LLMs under Test-Time Scaling
di: Hariri, Mohsen, et al.
Pubblicazione: (2026)

Compression Aware Certified Training
di: Xu, Changming, et al.
Pubblicazione: (2025)

GeoCert: Certified Geometric AI for Reliable Forecasting
di: Zhang, Regina, et al.
Pubblicazione: (2026)

Open-World Test-Time Training: Self-Training with Contrast Learning
di: Su, Houcheng, et al.
Pubblicazione: (2024)

Test-Time Training on Graphs with Large Language Models (LLMs)
di: Zhang, Jiaxin, et al.
Pubblicazione: (2024)

Training Guarantees of Neural Network Classification Two-Sample Tests by Kernel Analysis
di: Khurana, Varun, et al.
Pubblicazione: (2024)

Multi-Label Learning with Stronger Consistency Guarantees
di: Mao, Anqi, et al.
Pubblicazione: (2024)

Learning Neural Networks with Distribution Shift: Efficiently Certifiable Guarantees
di: Chandrasekaran, Gautam, et al.
Pubblicazione: (2025)

Certifying Counterfactual Bias in LLMs
di: Chaudhary, Isha, et al.
Pubblicazione: (2024)

Towards Certified Malware Detection: Provable Guarantees Against Evasion Attacks
di: Giri, Nandakrishna, et al.
Pubblicazione: (2026)

GF-Score: Certified Class-Conditional Robustness Evaluation with Fairness Guarantees
di: Shah, Arya, et al.
Pubblicazione: (2026)

Adaptive Test-Time Compute Allocation for Reasoning LLMs via Constrained Policy Optimization
di: Zhai, Zhiyuan, et al.
Pubblicazione: (2026)

Statistical Guarantees for Reasoning Probes on Looped Boolean Circuits
di: Kratsios, Anastasis, et al.
Pubblicazione: (2026)

Certifiable Boolean Reasoning Is Universal
di: Li, Wenhao, et al.
Pubblicazione: (2026)

Computational and Statistical Guarantees for Tensor-on-Tensor Regression with Tensor Train Decomposition
di: Qin, Zhen, et al.
Pubblicazione: (2024)

Statistical Guarantees for Offline Domain Randomization
di: Fickinger, Arnaud, et al.
Pubblicazione: (2025)

Efficient Evaluation of LLM Performance with Statistical Guarantees
di: Wu, Skyler, et al.
Pubblicazione: (2026)

Symmetry Guarantees Statistic Recovery in Variational Inference
di: Marks, Daniel, et al.
Pubblicazione: (2026)

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning
di: Zhang, Junru, et al.
Pubblicazione: (2025)

Decoupled Prototype Learning for Reliable Test-Time Adaptation
di: Wang, Guowei, et al.
Pubblicazione: (2024)

Mitigating Adaptive Attacks against Reasoning Models with Activation Consistency Training
di: Shah, Avidan, et al.
Pubblicazione: (2026)

Sample Compression for Self Certified Continual Learning
di: Comeau, Jacob, et al.
Pubblicazione: (2025)

Statistical Guarantees for High-Dimensional Stochastic Gradient Descent
di: Li, Jiaqi, et al.
Pubblicazione: (2025)

Active Seriation: Efficient Ordering Recovery with Statistical Guarantees
di: Cheshire, James, et al.
Pubblicazione: (2026)