Image de couverture de livre

Divergence Decoding: Inference-Time Unlearning via Auxiliary Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Merchant, Humzah, Levy, Bradford
Format:	Preprint
Publié:	2026
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

A Fast and Effective Solution to the Problem of Look-ahead Bias in LLMs
par: Merchant, Humzah, et autres
Publié: (2025)

Optimized Multi-Token Joint Decoding with Auxiliary Model for LLM Inference
par: Qin, Zongyue, et autres
Publié: (2024)

BeanCounter: A low-toxicity, large-scale, and open dataset of business-oriented text
par: Wang, Siyan, et autres
Publié: (2024)

Auxiliary Metrics Help Decoding Skill Neurons in the Wild
par: Zhao, Yixiu, et autres
Publié: (2025)

UCD: Unlearning in LLMs via Contrastive Decoding
par: Suriyakumar, Vinith M., et autres
Publié: (2025)

(G)I-DLE: Generative Inference via Distribution-preserving Logit Exclusion with KL Divergence Minimization for Constrained Decoding
par: Lee, Hanwool
Publié: (2025)

RKLD: Reverse KL-Divergence-based Knowledge Distillation for Unlearning Personal Information in Large Language Models
par: Wang, Bichen, et autres
Publié: (2024)

Revisiting Judge Decoding from First Principles via Training-Free Distributional Divergence
par: Sun, Shengyin, et autres
Publié: (2026)

Speculative Streaming: Fast LLM Inference without Auxiliary Models
par: Bhendawade, Nikhil, et autres
Publié: (2024)

Entropic-Time Inference: Self-Organizing Large Language Model Decoding Beyond Attention
par: Kiruluta, Andrew
Publié: (2026)

Humans and LLMs Diverge on Probabilistic Inferences
par: Kamath, Gaurav, et autres
Publié: (2026)

Mitigating Biases in Language Models via Bias Unlearning
par: Liu, Dianqing, et autres
Publié: (2025)

ParsTranslit: Truly Versatile Tajik-Farsi Transliteration
par: Merchant, Rayyan, et autres
Publié: (2025)

Knowing But Not Doing: Convergent Morality and Divergent Action in LLMs
par: Huang, Jen-tse, et autres
Publié: (2026)

OpenUnlearning: Accelerating LLM Unlearning via Unified Benchmarking of Methods and Metrics
par: Dorna, Vineeth, et autres
Publié: (2025)

Avoiding Copyright Infringement via Large Language Model Unlearning
par: Dou, Guangyao, et autres
Publié: (2024)

LoPA: Scaling dLLM Inference via Lookahead Parallel Decoding
par: Xu, Chenkai, et autres
Publié: (2025)

AdaSD: Adaptive Speculative Decoding for Efficient Language Model Inference
par: Lu, Kuan-Wei, et autres
Publié: (2025)

Tokens for Learning, Tokens for Unlearning: Mitigating Membership Inference Attacks in Large Language Models via Dual-Purpose Training
par: Tran, Toan, et autres
Publié: (2025)

LycheeDecode: Accelerating Long-Context LLM Inference via Hybrid-Head Sparse Decoding
par: Lin, Gang, et autres
Publié: (2026)

Improving Factuality in Large Language Models via Decoding-Time Hallucinatory and Truthful Comparators
par: Yang, Dingkang, et autres
Publié: (2024)

CSV-Decode: Certifiable Sub-Vocabulary Decoding for Efficient Large Language Model Inference
par: Liu, Dong, et autres
Publié: (2025)

N-gram-like Language Models Predict Reading Time Best
par: Michaelov, James A., et autres
Publié: (2026)

Unlearning What Matters: Token-Level Attribution for Precise Language Model Unlearning
par: Wu, Jiawei, et autres
Publié: (2026)

Mechanistic Unlearning: Robust Knowledge Unlearning and Editing via Mechanistic Localization
par: Guo, Phillip, et autres
Publié: (2024)

Eraser: Jailbreaking Defense in Large Language Models via Unlearning Harmful Knowledge
par: Lu, Weikai, et autres
Publié: (2024)

Accelerating Transformer Inference for Translation via Parallel Decoding
par: Santilli, Andrea, et autres
Publié: (2023)

FlashDecoding++: Faster Large Language Model Inference on GPUs
par: Hong, Ke, et autres
Publié: (2023)

Plato: Plan to Efficiently Decode for Large Language Model Inference
par: Jin, Shuowei, et autres
Publié: (2024)

Training and Inference Efficiency of Encoder-Decoder Speech Models
par: Żelasko, Piotr, et autres
Publié: (2025)

Speculative Decoding via Early-exiting for Faster LLM Inference with Thompson Sampling Control Mechanism
par: Liu, Jiahao, et autres
Publié: (2024)

Unlocking Efficiency in Large Language Model Inference: A Comprehensive Survey of Speculative Decoding
par: Xia, Heming, et autres
Publié: (2024)

Tutorial Proposal: Speculative Decoding for Efficient LLM Inference
par: Xia, Heming, et autres
Publié: (2025)

Learning-Time Encoding Shapes Unlearning in LLMs
par: Wu, Ruihan, et autres
Publié: (2025)

Model Unlearning via Sparse Autoencoder Subspace Guided Projections
par: Wang, Xu, et autres
Publié: (2025)

Dissecting Language Models: Machine Unlearning via Selective Pruning
par: Pochinkov, Nicholas, et autres
Publié: (2024)

Speculative Decoding for Multi-Sample Inference
par: Li, Yiwei, et autres
Publié: (2025)

TimeBill: Time-Budgeted Inference for Large Language Models
par: Fan, Qi, et autres
Publié: (2025)

AI-VERDE: A Gateway for Egalitarian Access to Large Language Model-Based Resources For Educational Institutions
par: Mithun, Paul, et autres
Publié: (2025)

Investigating the Feasibility of Mitigating Potential Copyright Infringement via Large Language Model Unlearning
par: Dou, Guangyao
Publié: (2024)