Cover Image

Decoding-time Realignment of Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liu, Tianlin, Guo, Shangmin, Bianco, Leonardo, Calandriello, Daniele, Berthet, Quentin, Llinares, Felipe, Hoffmann, Jessica, Dixon, Lucas, Valko, Michal, Blondel, Mathieu
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Direct Language Model Alignment from Online AI Feedback
by: Guo, Shangmin, et al.
Published: (2024)

On Teacher Hacking in Language Model Distillation
by: Tiapkin, Daniil, et al.
Published: (2025)

Large-scale semi-supervised learning with online spectral graph sparsification
by: Calandriello, Daniele, et al.
Published: (2026)

Analysis of Nystrom method with sequential ridge leverage scores
by: Calandriello, Daniele, et al.
Published: (2026)

Pack only the essentials: Adaptive dictionary learning for kernel ridge regression
by: Calandriello, Daniele, et al.
Published: (2026)

Structured Context Recomposition for Large Language Models Using Probabilistic Layer Realignment
by: Teel, Jonathan, et al.
Published: (2025)

Improved large-scale graph learning through ridge spectral sparsification
by: Calandriello, Daniele, et al.
Published: (2026)

Flexible Realignment of Language Models
by: Zhu, Wenhong, et al.
Published: (2025)

The Elements of Differentiable Programming
by: Blondel, Mathieu, et al.
Published: (2024)

Implicit Diffusion: Efficient Optimization through Stochastic Sampling
by: Marion, Pierre, et al.
Published: (2024)

Bias Amplification in Language Model Evolution: An Iterated Learning Perspective
by: Ren, Yi, et al.
Published: (2024)

Latent Convergence Modulation in Large Language Models: A Novel Approach to Iterative Contextual Realignment
by: Porretta, Patricia, et al.
Published: (2025)

NLSR: Neuron-Level Safety Realignment of Large Language Models Against Harmful Fine-Tuning
by: Yi, Xin, et al.
Published: (2024)

Joint Learning of Energy-based Models and their Partition Function
by: Sander, Michael E., et al.
Published: (2025)

Emergently Misaligned Language Models Show Behavioral Self-Awareness That Shifts With Subsequent Realignment
by: Vaugrante, Laurène, et al.
Published: (2026)

AlignFreeze: Navigating the Impact of Realignment on the Layers of Multilingual Models Across Diverse Languages
by: Bakos, Steve, et al.
Published: (2025)

Routers in Vision Mixture of Experts: An Empirical Study
by: Liu, Tianlin, et al.
Published: (2024)

DeAL: Decoding-time Alignment for Large Language Models
by: Huang, James Y., et al.
Published: (2024)

A Study on Hidden Layer Distillation for Large Language Model Pre-Training
by: Guigon, Maxime, et al.
Published: (2026)

Autoregressive Language Models are Secretly Energy-Based Models: Insights into the Lookahead Capabilities of Next-Token Prediction
by: Blondel, Mathieu, et al.
Published: (2025)

The Realignment Problem: When Right becomes Wrong in LLMs
by: Sharma, Aakash Sen, et al.
Published: (2025)

Rethinking what Matters: Effective and Robust Multilingual Realignment for Low-Resource Languages
by: Nguyen, Quang Phuoc, et al.
Published: (2025)

Hierarchical Safety Realignment: Lightweight Restoration of Safety in Pruned Large Vision-Language Models
by: Li, Yue, et al.
Published: (2025)

Detecting Hallucination and Coverage Errors in Retrieval Augmented Generation for Controversial Topics
by: Chang, Tyler A., et al.
Published: (2024)

Scalable Influence and Fact Tracing for Large Language Model Pretraining
by: Chang, Tyler A., et al.
Published: (2024)

Purifying Large Language Models by Ensembling a Small Language Model
by: Li, Tianlin, et al.
Published: (2024)

Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models
by: Ghandeharioun, Asma, et al.
Published: (2024)

The Mysterious Case of Neuron 1512: Injectable Realignment Architectures Reveal Internal Characteristics of Meta's Llama 2 Model
by: Smith, Brenden, et al.
Published: (2024)

GeoAlign: Geometric Feature Realignment for MLLM Spatial Reasoning
by: Liu, Zhaochen, et al.
Published: (2026)

Model-free Posterior Sampling via Learning Rate Randomization
by: Tiapkin, Daniil, et al.
Published: (2023)

EmoLLMs: A Series of Emotional Large Language Models and Annotation Tools for Comprehensive Affective Analysis
by: Liu, Zhiwei, et al.
Published: (2024)

Proximal Point Nash Learning from Human Feedback
by: Tiapkin, Daniil, et al.
Published: (2025)

Demonstration-Regularized RL
by: Tiapkin, Daniil, et al.
Published: (2023)

Towards Interpretable Mental Health Analysis with Large Language Models
by: Yang, Kailai, et al.
Published: (2023)

Think Before You Lie: How Reasoning Leads to Honesty
by: Yuan, Ann, et al.
Published: (2026)

Encoder-Decoder or Decoder-Only? Revisiting Encoder-Decoder Large Language Model
by: Zhang, Biao, et al.
Published: (2025)

ART: Attention Run-time Termination for Efficient Large Language Model Decoding
by: Qiu, Chen, et al.
Published: (2026)

MentaLLaMA: Interpretable Mental Health Analysis on Social Media with Large Language Models
by: Yang, Kailai, et al.
Published: (2023)

Bandits on graphs and structures
by: Valko, Michal
Published: (2026)

Adaptive graph-based algorithms for conditional anomaly detection and semi-supervised learning
by: Valko, Michal
Published: (2026)