Imagen de Portada

Conditional Performance Guarantee for Large Reasoning Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Huang, Jianguo, Zeng, Hao, Jing, Bingyi, Wei, Hongxin, An, Bo
Formato:	Preprint
Publicado:	2026
Materias:	Artificial Intelligence Statistics Theory
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

On the Provable Performance Guarantee of Efficient Reasoning Models
por: Zeng, Hao, et al.
Publicado: (2025)

RACER: Risk-Aware Calibrated Efficient Routing for Large Language Models
por: Hao, Sai, et al.
Publicado: (2026)

HyPAC: Cost-Efficient LLMs-Human Hybrid Annotation with PAC Error Guarantees
por: Zeng, Hao, et al.
Publicado: (2026)

Parametric Scaling Law of Tuning Bias in Conformal Prediction
por: Zeng, Hao, et al.
Publicado: (2025)

TorchCP: A Python Library for Conformal Prediction
por: Huang, Jianguo, et al.
Publicado: (2024)

Multi-Condition Conformal Selection
por: Hao, Qingyang, et al.
Publicado: (2025)

Anytime Safe PAC Efficient Reasoning
por: Yu, Chengyao, et al.
Publicado: (2026)

Accelerated Online Risk-Averse Policy Evaluation in POMDPs with Theoretical Guarantees and Novel CVaR Bounds
por: Pariente, Yaacov, et al.
Publicado: (2026)

A note on the impossibility of conditional PAC-efficient reasoning in large language models
por: Zeng, Hao
Publicado: (2025)

Canonical Representations of Markovian Structural Causal Models: A Framework for Counterfactual Reasoning
por: de Lara, Lucas
Publicado: (2025)

A Computational Theory for Efficient Mini Agent Evaluation with Causal Guarantees
por: Yan, Hedong
Publicado: (2025)

Can Generative Artificial Intelligence Survive Data Contamination? Theoretical Guarantees under Contaminated Recursive Training
por: Wang, Kevin, et al.
Publicado: (2026)

A General Framework on Conditions for Constraint-based Causal Learning
por: Teh, Kai Z., et al.
Publicado: (2024)

Guaranteed Recovery of Unambiguous Clusters
por: Mazooji, Kayvon, et al.
Publicado: (2025)

Fine-tuning can Help Detect Pretraining Data from Large Language Models
por: Zhang, Hengxiang, et al.
Publicado: (2024)

Distribution-consistency Structural Causal Models
por: Gong, Heyang, et al.
Publicado: (2024)

A Likelihood Based Approach to Distribution Regression Using Conditional Deep Generative Models
por: Kumar, Shivam, et al.
Publicado: (2024)

A Unified Pair-GRPO Family: From Implicit to Explicit Preference Constraints for Stable and General RL Alignment
por: Yu, Hao
Publicado: (2026)

Path Regularization: A Near-Complete and Optimal Nonasymptotic Generalization Theory for Multilayer Neural Networks and Double Descent Phenomenon
por: Yu, Hao
Publicado: (2025)

Model-agnostic Selective Labeling with Provable Statistical Guarantees
por: Huang, Huipeng, et al.
Publicado: (2025)

Improved Guarantees for Heterogeneous Treatment-Effect Estimation via Matrix Completion
por: Mehrotra, Anay, et al.
Publicado: (2026)

Navigating the Exploration-Exploitation Tradeoff in Inference-Time Scaling of Diffusion Models
por: Su, Xun, et al.
Publicado: (2025)

Reject, Resample, Repeat: Understanding Parallel Reasoning in Language Model Inference
por: Golowich, Noah, et al.
Publicado: (2026)

Causal Sufficiency and Necessity Improves Chain-of-Thought Reasoning
por: Yu, Xiangning, et al.
Publicado: (2025)

Bethe Ansatz with a Large Language Model
por: Pozsgay, Balázs, et al.
Publicado: (2026)

Retraining as Approximate Bayesian Inference
por: Katz, Harrison
Publicado: (2026)

About the Cost of Central Privacy in Density Estimation
por: Lalanne, Clément, et al.
Publicado: (2023)

A Measure-Theoretic Axiomatisation of Causality
por: Park, Junhyung, et al.
Publicado: (2023)

Identifiability of total effects from abstractions of time series causal graphs
por: Assaad, Charles K., et al.
Publicado: (2023)

Note on the identification of total effect in Cluster-DAGs with cycles
por: Yvernes, Clément
Publicado: (2025)

Identifiability by common backdoor in summary causal graphs of time series
por: Yvernes, Clément, et al.
Publicado: (2025)

Complete Characterization for Adjustment in Summary Causal Graphs of Time Series
por: Yvernes, Clément, et al.
Publicado: (2025)

Stochastic Direct Search Method for Blind Resource Allocation
por: Achddou, Juliette, et al.
Publicado: (2022)

Statistical Inference for Misspecified Contextual Bandits
por: Guo, Yongyi, et al.
Publicado: (2025)

Physics-informed machine learning as a kernel method
por: Doumèche, Nathan, et al.
Publicado: (2024)

Provable Training Data Identification for Large Language Models
por: Liu, Zhenlong, et al.
Publicado: (2025)

Reasoning with Sampling: Cutting at Decision Points
por: Zhou, Felix, et al.
Publicado: (2026)

Evaluating LLMs When They Do Not Know the Answer: Statistical Evaluation of Mathematical Reasoning via Comparative Signals
por: Dong, Zihan, et al.
Publicado: (2026)

The Geometry of Knowing: From Possibilistic Ignorance to Probabilistic Certainty -- A Measure-Theoretic Framework for Epistemic Convergence
por: Jah, Moriba Kemessia
Publicado: (2026)

Don't Pass@k: A Bayesian Framework for Large Language Model Evaluation
por: Hariri, Mohsen, et al.
Publicado: (2025)