Cover Image

Test-Time Alignment of LLMs via Sampling-Based Optimal Control in pre-logit space

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kanai, Sekitoshi, Yoshida, Tsukasa, Takahashi, Hiroshi, Kuroki, Haru, Hashimoto, Kazumune
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Evaluating Time-Series Training Dataset through Lens of Spectrum in Deep State Space Models
by: Kanai, Sekitoshi, et al.
Published: (2024)

Relative Density Ratio Optimization for Stable and Statistically Consistent Model Alignment
by: Takahashi, Hiroshi, et al.
Published: (2026)

Post-pre-training for Modality Alignment in Vision-Language Foundation Models
by: Yamaguchi, Shin'ya, et al.
Published: (2025)

Long-term Safe Reinforcement Learning with Binary Feedback
by: Wachi, Akifumi, et al.
Published: (2024)

Transfer Learning with Pre-trained Conditional Generative Models
by: Yamaguchi, Shin'ya, et al.
Published: (2022)

Adaptive Random Feature Regularization on Fine-tuning Deep Neural Networks
by: Yamaguchi, Shin'ya, et al.
Published: (2024)

Complementing reinforcement learning with SFT through logit averaging in the post training of LLMs
by: Gan, Xingwei, et al.
Published: (2026)

Sample Efficient Preference Alignment in LLMs via Active Exploration
by: Mehta, Viraj, et al.
Published: (2023)

Sample-Efficient Alignment for LLMs
by: Liu, Zichen, et al.
Published: (2024)

GAC: Stabilizing Asynchronous RL Training for LLMs via Gradient Alignment Control
by: Xu, Haofeng, et al.
Published: (2026)

CAP: Controllable Alignment Prompting for Unlearning in LLMs
by: Wang, Zhaokun, et al.
Published: (2026)

Conditional Factuality Controlled LLMs with Generalization Certificates via Conformal Sampling
by: Ye, Kai, et al.
Published: (2026)

Test-Time Safety Alignment
by: Saglam, Baturay, et al.
Published: (2026)

Reasoning on a Budget: A Survey of Adaptive and Controllable Test-Time Compute in LLMs
by: Alomrani, Mohammad Ali, et al.
Published: (2025)

Test-Time Scaling in Diffusion LLMs via Hidden Semi-Autoregressive Experts
by: Lee, Jihoon, et al.
Published: (2025)

PARM: Multi-Objective Test-Time Alignment via Preference-Aware Autoregressive Reward Model
by: Lin, Baijiong, et al.
Published: (2025)

Revisiting the (Sub)Optimality of Best-of-N for Inference-Time Alignment
by: Sriraman, Ved, et al.
Published: (2026)

Scalable Simulation-Based Model Inference with Test-Time Complexity Control
by: Gloeckler, Manuel, et al.
Published: (2026)

Enhancing Time Series Forecasting via Multi-Level Text Alignment with LLMs
by: Zhao, Taibiao, et al.
Published: (2025)

Bidirectional Decoding: Improving Action Chunking via Guided Test-Time Sampling
by: Liu, Yuejiang, et al.
Published: (2024)

SparsePO: Controlling Preference Alignment of LLMs via Sparse Token Masks
by: Christopoulou, Fenia, et al.
Published: (2024)

Thompson Sampling via Fine-Tuning of LLMs
by: Menet, Nicolas, et al.
Published: (2025)

MM-LMPC: Multi-Modal Learning Model Predictive Control via Bandit-Based Mode Selection
by: Hashimoto, Wataru, et al.
Published: (2025)

Multi-Value Alignment for LLMs via Value Decorrelation and Extrapolation
by: Xu, Hefei, et al.
Published: (2025)

Is Best-of-N the Best of Them? Coverage, Scaling, and Optimality in Inference-Time Alignment
by: Huang, Audrey, et al.
Published: (2025)

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

Efficiently Learning at Test-Time: Active Fine-Tuning of LLMs
by: Hübotter, Jonas, et al.
Published: (2024)

C-MORAL: Controllable Multi-Objective Molecular Optimization with Reinforcement Alignment for LLMs
by: Gao, Rui, et al.
Published: (2026)

Conflict-Aware Pseudo Labeling via Optimal Transport for Entity Alignment
by: Ding, Qijie, et al.
Published: (2022)

Rethinking Optimal Verification Granularity for Compute-Efficient Test-Time Scaling
by: Chen, Hao Mark, et al.
Published: (2025)

POEM: Explore Unexplored Reliable Samples to Enhance Test-Time Adaptation
by: Yi, Chang'an, et al.
Published: (2025)

Lookahead Sample Reward Guidance for Test-Time Scaling of Diffusion Models
by: Kim, Yeongmin, et al.
Published: (2026)

Immune: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment
by: Ghosal, Soumya Suvra, et al.
Published: (2024)

Test-time Correlation Alignment
by: You, Linjing, et al.
Published: (2025)

Lyapunov-Guided Self-Alignment: Test-Time Adaptation for Offline Safe Reinforcement Learning
by: Han, Seungyub, et al.
Published: (2026)

On the Role of Temperature Sampling in Test-Time Scaling
by: Wu, Yuheng, et al.
Published: (2025)

Local Linearity of LLMs Enables Activation Steering via Model-Based Linear Optimal Control
by: Skifstad, Julian, et al.
Published: (2026)

GuidedSampling: Steering LLMs Towards Diverse Candidate Solutions at Inference-Time
by: Handa, Divij, et al.
Published: (2025)

Inference-Time Alignment Control for Diffusion Models with Reinforcement Learning Guidance
by: Jin, Luozhijie, et al.
Published: (2025)

Steering Frozen LLMs: Adaptive Social Alignment via Online Prompt Routing
by: Zhang, Zeyu, et al.
Published: (2026)