Copertina

Harmonizing Multi-Objective LLM Unlearning via Unified Domain Representation and Bidirectional Logit Distillation

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Zhong, Yisheng, Liu, Sijia, Zhu, Zhuangdi
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

DUET: Distilled LLM Unlearning from an Efficiently Contextualized Teacher
di: Zhong, Yisheng, et al.
Pubblicazione: (2026)

Hierarchical Federated Unlearning for Large Language Models
di: Zhong, Yisheng, et al.
Pubblicazione: (2025)

SHRED: Retain-Set-Free Unlearning via Self-Distillation with Logit Demotion
di: Hu, Zizhao, et al.
Pubblicazione: (2026)

Unlearners Can Lie: Evaluating and Improving Honesty in LLM Unlearning
di: Gu, Renjie, et al.
Pubblicazione: (2026)

How Hard Can It Be? Hardness-Aware Multi-Objective Unlearning
di: Chen, Jiangwei, et al.
Pubblicazione: (2026)

Reversing the Forget-Retain Objectives: An Efficient LLM Unlearning Framework from Logit Difference
di: Ji, Jiabao, et al.
Pubblicazione: (2024)

OGLS-SD: On-Policy Self-Distillation with Outcome-Guided Logit Steering for LLM Reasoning
di: Yang, Yuxiao, et al.
Pubblicazione: (2026)

SCDM: Unified Representation Learning for EEG-to-fNIRS Cross-Modal Generation in MI-BCIs
di: Li, Yisheng, et al.
Pubblicazione: (2024)

Meta-Aligner: Bidirectional Preference-Policy Optimization for Multi-Objective LLMs Alignment
di: Xu, Wenzhe, et al.
Pubblicazione: (2026)

Logit Distillation on Manifolds: Mapping by Learning
di: Yang, Yiru, et al.
Pubblicazione: (2026)

Unlearning via Sparse Representations
di: Shah, Vedant, et al.
Pubblicazione: (2023)

Attention Smoothing Is All You Need For Unlearning
di: Zade, Saleh Zare, et al.
Pubblicazione: (2026)

Distillation Robustifies Unlearning
di: Lee, Bruce W., et al.
Pubblicazione: (2025)

Logit Distance Bounds Representational Similarity
di: Nielsen, Beatrix M. G., et al.
Pubblicazione: (2026)

Peak-Controlled Logits Poisoning Attack in Federated Distillation
di: Tang, Yuhan, et al.
Pubblicazione: (2024)

Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning
di: Fan, Chongyu, et al.
Pubblicazione: (2024)

Multi-Objective Large Language Model Unlearning
di: Pan, Zibin, et al.
Pubblicazione: (2024)

LLM Unlearning Reveals a Stronger-Than-Expected Coreset Effect in Current Benchmarks
di: Pal, Soumyadeep, et al.
Pubblicazione: (2025)

SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation
di: Fan, Chongyu, et al.
Pubblicazione: (2023)

Beyond Sharp Minima: Robust LLM Unlearning via Feedback-Guided Multi-Point Optimization
di: Wu, Wenhan, et al.
Pubblicazione: (2025)

Nd-BiMamba2: A Unified Bidirectional Architecture for Multi-Dimensional Data Processing
di: Liu, Hao
Pubblicazione: (2024)

Bidirectional Distillation: A Mixed-Play Framework for Multi-Agent Generalizable Behaviors
di: Feng, Lang, et al.
Pubblicazione: (2025)

LLM Unlearning via Neural Activation Redirection
di: Shen, William F., et al.
Pubblicazione: (2025)

Bidirectional Hierarchical Protein Multi-Modal Representation Learning
di: Liu, Xuefeng, et al.
Pubblicazione: (2025)

EchoMamba4Rec: Harmonizing Bidirectional State Space Models with Spectral Filtering for Advanced Sequential Recommendation
di: Wang, Yuda, et al.
Pubblicazione: (2024)

Unified Parameter-Efficient Unlearning for LLMs
di: Ding, Chenlu, et al.
Pubblicazione: (2024)

GEAR: Granularity-Adaptive Advantage Reweighting for LLM Agents via Self-Distillation
di: Li, Sijia, et al.
Pubblicazione: (2026)

Safety Mirage: How Spurious Correlations Undermine VLM Safety Fine-Tuning and Can Be Mitigated by Machine Unlearning
di: Chen, Yiwei, et al.
Pubblicazione: (2025)

Agentic Unlearning: When LLM Agent Meets Machine Unlearning
di: Wang, Bin, et al.
Pubblicazione: (2026)

Sustained Gradient Alignment Mediates Subliminal Learning in a Multi-Step Setting: Evidence from MNIST Auxiliary Logit Distillation Experiment
di: Kitkana, Chayanon, et al.
Pubblicazione: (2026)

LLM Unlearning Without an Expert Curated Dataset
di: Zhu, Xiaoyuan, et al.
Pubblicazione: (2025)

Uncovering Logit Suppression Vulnerabilities in LLM Safety Alignment
di: Li, Yuxi, et al.
Pubblicazione: (2024)

QuickDrop: Efficient Federated Unlearning by Integrated Dataset Distillation
di: Dhasade, Akash, et al.
Pubblicazione: (2023)

LLM Unlearning via Loss Adjustment with Only Forget Data
di: Wang, Yaxuan, et al.
Pubblicazione: (2024)

Bidirectional Generative Pre-training for Improving Healthcare Time-series Representation Learning
di: Song, Ziyang, et al.
Pubblicazione: (2024)

Machine Unlearning via Null Space Calibration
di: Chen, Huiqiang, et al.
Pubblicazione: (2024)

A Unifying Post-Processing Framework for Multi-Objective Learn-to-Defer Problems
di: Charusaie, Mohammad-Amin, et al.
Pubblicazione: (2024)

Towards Mitigating Excessive Forgetting in LLM Unlearning via Entanglement-Guidance with Proxy Constraint
di: Liu, Zhihao, et al.
Pubblicazione: (2025)

Evidence-Gated LLM Priors for Multi-Objective Bayesian Optimization
di: Chen, Jiangyu, et al.
Pubblicazione: (2026)

Exploring Criteria of Loss Reweighting to Enhance LLM Unlearning
di: Yang, Puning, et al.
Pubblicazione: (2025)