Cover Image

Guided Speculative Inference for Efficient Test-Time Alignment of LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Geuter, Jonathan, Mroueh, Youssef, Alvarez-Melis, David
Format:	Preprint
Published:	2025
Subjects:	Machine Learning I.2.7
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Random Scaling of Emergent Capabilities
by: Zhao, Rosie, et al.
Published: (2025)

Amulet: ReAlignment During Test Time for Personalized Preference Adaptation of LLMs
by: Zhang, Zhaowei, et al.
Published: (2025)

Latent Instruction Representation Alignment: defending against jailbreaks, backdoors and undesired knowledge in LLMs
by: Easley, Eric, et al.
Published: (2026)

Aligning LLMs on a Budget: Inference-Time Alignment with Heuristic Reward Models
by: Nakamura, Mason, et al.
Published: (2025)

EvilGenie: A Reward Hacking Benchmark
by: Gabor, Jonathan, et al.
Published: (2025)

Attention Drift: What Autoregressive Speculative Decoding Models Learn
by: Eldenk, Doğaç, et al.
Published: (2026)

CopySpec: Accelerating LLMs with Speculative Copy-and-Paste Without Compromising Quality
by: Dumitru, Razvan-Gabriel, et al.
Published: (2025)

Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMs
by: Ahmadian, Arash, et al.
Published: (2024)

Quantization Undoes Alignment: Bias Emergence in Compressed LLMs Across Models and Precision Levels
by: Rath, Plawan Kumar, et al.
Published: (2026)

Mr. Snuffleupagus at SemEval-2025 Task 4: Unlearning Factual Knowledge from LLMs Using Adaptive RMU
by: Dosajh, Arjun, et al.
Published: (2025)

CG-TTRL: Context-Guided Test-Time Reinforcement Learning for On-Device Large Language Models
by: Hosseini, Peyman, et al.
Published: (2025)

Entropy-Based Measurement of Value Drift and Alignment Work in Large Language Models
by: Fadli, Samih
Published: (2025)

Merge-Bench: Resolve Merge Conflicts with Large Language Models
by: Schesch, Benedikt, et al.
Published: (2026)

Behavioural Analysis of Alignment Faking
by: Hadida, Nathaniel Mitrani, et al.
Published: (2026)

When Models Can't Follow: Testing Instruction Adherence Across 256 LLMs
by: Young, Richard J., et al.
Published: (2025)

A Statistical Framework for Alignment with Biased AI Feedback
by: Xia, Xintao, et al.
Published: (2026)

Resonant Context Anchoring: Decoupling Attention Routing and Signal Gain at Inference Time
by: Zhao, Mingkuan, et al.
Published: (2026)

FastGRPO: Accelerating Policy Optimization via Concurrency-aware Speculative Decoding and Online Draft Learning
by: Zhang, Yizhou, et al.
Published: (2025)

Efficient Solutions For An Intriguing Failure of LLMs: Long Context Window Does Not Mean LLMs Can Analyze Long Sequences Flawlessly
by: Hosseini, Peyman, et al.
Published: (2024)

Structure-Guided Entity Resolution: Fine-Tuning LLMs for Robust Name Matching in Complex Linguistic Contexts
by: Chourasia, Shivam, et al.
Published: (2026)

QuAnTS: Question Answering on Time Series
by: Divo, Felix, et al.
Published: (2025)

Token Erasure as a Footprint of Implicit Vocabulary Items in LLMs
by: Feucht, Sheridan, et al.
Published: (2024)

Memory-Efficient Differentially Private Training with Gradient Random Projection
by: Mulrooney, Alex, et al.
Published: (2025)

Multilingual LLMs Inherently Reward In-Language Time-Sensitive Semantic Alignment for Low-Resource Languages
by: Bajpai, Ashutosh, et al.
Published: (2024)

ACE: Exploring Activation Cosine Similarity and Variance for Accurate and Calibration-Efficient LLM Pruning
by: Mi, Zhendong, et al.
Published: (2025)

FlexQuant: A Flexible and Efficient Dynamic Precision Switching Framework for LLM Quantization
by: Liu, Fangxin, et al.
Published: (2025)

Why LoRA Resists Label Noise: A Theoretical Framework for Noise-Robust Parameter-Efficient Fine-Tuning
by: Steele, Brady
Published: (2026)

SSSD: Simply-Scalable Speculative Decoding
by: Marzollo, Michele, et al.
Published: (2024)

Evaluating the Efficacy of Hybrid Deep Learning Models in Distinguishing AI-Generated Text
by: Oketunji, Abiodun Finbarrs
Published: (2023)

FED-FSTQ: Fisher-Guided Token Quantization for Communication-Efficient Federated Fine-Tuning of LLMs on Edge Devices
by: Li, Changyu, et al.
Published: (2026)

SCULPT: Constraint-Guided Pruned MCTS that Carves Efficient Paths for Mathematical Reasoning
by: Fang, Qitong, et al.
Published: (2026)

Generalizable LLM Learning of Graph Synthetic Data with Post-training Alignment
by: Zhang, Yizhuo, et al.
Published: (2025)

Random Heterogeneous Neurochaos Learning Architecture for Data Classification
by: S, Remya Ajai A, et al.
Published: (2024)

The Hidden Attention of Mamba Models
by: Ali, Ameen, et al.
Published: (2024)

Ambiguity in LLMs is a concept missing problem
by: Hu, Zhibo, et al.
Published: (2025)

Reinforcement Learning for Latent-Space Thinking in LLMs
by: Özeren, Enes, et al.
Published: (2025)

LLM Unlearning on Noisy Forget Sets: A Study of Incomplete, Rewritten, and Watermarked Data
by: Wang, Changsheng, et al.
Published: (2025)

Procedural Environment Generation for Tool-Use Agents
by: Sullivan, Michael, et al.
Published: (2025)

Unsupervised Evaluation of Multi-Turn Objective-Driven Interactions
by: Soroka, Emi, et al.
Published: (2025)

Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining
by: Zhao, Rosie, et al.
Published: (2025)