Image de couverture de livre

When to Trust the Cheap Check: Weak and Strong Verification for Reasoning

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Kiyani, Shayan, Noorani, Sima, Pappas, George, Hassani, Hamed
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Conformal Prediction Beyond the Seen: A Missing Mass Perspective for Uncertainty Quantification in Generative Models
par: Noorani, Sima, et autres
Publié: (2025)

Human-AI Collaborative Uncertainty Quantification
par: Noorani, Sima, et autres
Publié: (2025)

Multi-Round Human-AI Collaboration with User-Specified Requirements
par: Noorani, Sima, et autres
Publié: (2026)

Conformal Prediction with Learned Features
par: Kiyani, Shayan, et autres
Publié: (2024)

Length Optimization in Conformal Prediction
par: Kiyani, Shayan, et autres
Publié: (2024)

Decision Theoretic Foundations for Conformal Prediction: Optimal Uncertainty Quantification for Risk-Averse Agents
par: Kiyani, Shayan, et autres
Publié: (2025)

Robust Decision Making with Partially Calibrated Forecasts
par: Kiyani, Shayan, et autres
Publié: (2025)

Conformal Inference under High-Dimensional Covariate Shifts via Likelihood-Ratio Regularization
par: Joshi, Sunay, et autres
Publié: (2025)

Adversarial Reasoning at Jailbreaking Time
par: Sabbaghi, Mahdi, et autres
Publié: (2025)

SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks
par: Robey, Alexander, et autres
Publié: (2023)

Conformal Risk Minimization with Variance Reduction
par: Noorani, Sima, et autres
Publié: (2024)

Temporal Difference Learning with Compressed Updates: Error-Feedback meets Reinforcement Learning
par: Mitra, Aritra, et autres
Publié: (2023)

Jailbreaking Black Box Large Language Models in Twenty Queries
par: Chao, Patrick, et autres
Publié: (2023)

Generalizing Trust: Weak-to-Strong Trustworthiness in Language Models
par: Pawelczyk, Martin, et autres
Publié: (2024)

When Is Rank-1 Steering Cheap? Geometry, Granularity, and Budgeted Search
par: Robertson, John T., et autres
Publié: (2026)

When Can LLMs Learn to Reason with Weak Supervision?
par: Rahman, Salman, et autres
Publié: (2026)

On the Mechanisms of Weak-to-Strong Generalization: A Theoretical Perspective
par: Moniri, Behrad, et autres
Publié: (2025)

Self-Verification Dilemma: Experience-Driven Suppression of Overused Checking in LLM Reasoning
par: Long, Quanyu, et autres
Publié: (2026)

Evaluating the Performance of Large Language Models via Debates
par: Moniri, Behrad, et autres
Publié: (2024)

Learning When to Trust in Contextual Bandits
par: Ghasemi, Majid, et autres
Publié: (2026)

Mixture of Weak & Strong Experts on Graphs
par: Zeng, Hanqing, et autres
Publié: (2023)

Quantifying the Gain in Weak-to-Strong Generalization
par: Charikar, Moses, et autres
Publié: (2024)

When To Solve, When To Verify: Compute-Optimal Problem Solving and Generative Verification for LLM Reasoning
par: Singhi, Nishad, et autres
Publié: (2025)

OptiGradTrust: Byzantine-Robust Federated Learning with Multi-Feature Gradient Analysis and Reinforcement Learning-Based Trust Weighting
par: Karami, Mohammad, et autres
Publié: (2025)

Distributed Risk-Sensitive Safety Filters for Uncertain Discrete-Time Systems
par: Lederer, Armin, et autres
Publié: (2025)

Risk-Sensitive Reinforcement Learning with Exponential Criteria
par: Noorani, Erfaun, et autres
Publié: (2022)

Weak-to-Strong Generalization under Distribution Shifts
par: Jeon, Myeongho, et autres
Publié: (2025)

How Do Latent Reasoning Methods Perform Under Weak and Strong Supervision?
par: Cui, Yingqian, et autres
Publié: (2026)

Weak-to-Strong Generalization Through the Data-Centric Lens
par: Shin, Changho, et autres
Publié: (2024)

Optimizing the Optimizer for Physics-Informed Neural Networks and Kolmogorov-Arnold Networks
par: Kiyani, Elham, et autres
Publié: (2025)

BrowserArena: Evaluating LLM Agents on Real-World Web Navigation Tasks
par: Anupam, Sagnik, et autres
Publié: (2025)

Conformal Information Pursuit for Interactively Guiding Large Language Models
par: Chan, Kwan Ho Ryan, et autres
Publié: (2025)

Conformal Alignment: Knowing When to Trust Foundation Models with Guarantees
par: Gui, Yu, et autres
Publié: (2024)

Rich Insights from Cheap Signals: Efficient Evaluations via Tensor Factorization
par: Polo, Felipe Maia, et autres
Publié: (2026)

WST: Weak-to-Strong Knowledge Transfer via Reinforcement Learning
par: Ge, Haosen, et autres
Publié: (2025)

InfoSFT: Learn More and Forget Less with Information-Aware Token Weighting
par: Sabbaghi, Mahdi, et autres
Publié: (2026)

Robust Policy Optimization to Prevent Catastrophic Forgetting
par: Sabbaghi, Mahdi, et autres
Publié: (2026)

Crack Path Prediction with Operator Learning using Discrete Particle System data Generation
par: Kiyani, Elham, et autres
Publié: (2025)

Reasoned Safety Alignment: Ensuring Jailbreak Defense via Answer-Then-Check
par: Cao, Chentao, et autres
Publié: (2025)

One-Token Verification for Reasoning Correctness Estimation
par: Zhuang, Zhan, et autres
Publié: (2026)