Cover Image

Do LLMs Really Forget? Evaluating Unlearning with Knowledge Correlation and Confidence Awareness

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wei, Rongzhe, Niu, Peizhi, Hsu, Hans Hao-Hsun, Wu, Ruihan, Yin, Haoteng, Ghassemi, Mohsen, Li, Yifan, Potluru, Vamsi K., Chien, Eli, Chaudhuri, Kamalika, Milenkovic, Olgica, Li, Pan
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning
by: Wei, Rongzhe, et al.
Published: (2024)

The Trojan Knowledge: Bypassing Commercial LLM Guardrails via Harmless Prompt Weaving and Adaptive Tree Search
by: Wei, Rongzhe, et al.
Published: (2025)

On the Inherent Privacy Properties of Discrete Denoising Diffusion Models
by: Wei, Rongzhe, et al.
Published: (2023)

Guarding Multiple Secrets: Enhanced Summary Statistic Privacy for Data Sharing
by: Wang, Shuaiqi, et al.
Published: (2024)

Privately Learning from Graphs with Applications in Fine-tuning Large Language Models
by: Yin, Haoteng, et al.
Published: (2024)

Graph Transductive Defense: a Two-Stage Defense for Graph Membership Inference Attacks
by: Niu, Peizhi, et al.
Published: (2024)

Learning-Time Encoding Shapes Unlearning in LLMs
by: Wu, Ruihan, et al.
Published: (2025)

GUARD: Guided Unlearning and Retention via Data Attribution for Large Language Models
by: Niu, Peizhi, et al.
Published: (2025)

Differentially Private Relational Learning with Entity-level Privacy Guarantees
by: Huang, Yinan, et al.
Published: (2025)

Evaluating Deep Unlearning in Large Language Models
by: Wu, Ruihan, et al.
Published: (2024)

One Turn Too Late: Response-Aware Defense Against Hidden Malicious Intent in Multi-Turn Dialogue
by: Shen, Xinjie, et al.
Published: (2026)

Federated Classification in Hyperbolic Spaces via Secure Aggregation of Convex Hulls
by: Prakash, Saurav, et al.
Published: (2023)

Distributionally and Adversarially Robust Logistic Regression via Intersecting Wasserstein Balls
by: Selvi, Aras, et al.
Published: (2024)

Multiple sequences Prophet Inequality Under Observation Constraints
by: Tsopelakos, Aristomenis, et al.
Published: (2024)

DMol: A Highly Efficient and Chemical Motif-Preserving Molecule Generation Platform
by: Niu, Peizhi, et al.
Published: (2025)

Differentially Private Graph Diffusion with Applications in Personalized PageRanks
by: Wei, Rongzhe, et al.
Published: (2024)

Better Membership Inference Privacy Measurement through Discrepancy
by: Wu, Ruihan, et al.
Published: (2024)

Influence-based Attributions can be Manipulated
by: Yadav, Chhavi, et al.
Published: (2024)

WaveletDiff: Multilevel Wavelet Diffusion For Time Series Generation
by: Wang, Yu-Hsiang, et al.
Published: (2025)

Positional Identifiability from Pairwise Collision Data
by: Li, Yun-Han, et al.
Published: (2026)

Auditing and Enforcing Conditional Fairness via Optimal Transport
by: Ghassemi, Mohsen, et al.
Published: (2024)

DPrivBench: Benchmarking LLMs' Reasoning for Differential Privacy
by: Wang, Erchi, et al.
Published: (2026)

Perturbation-Resilient Trades for Dynamic Service Balancing
by: Sima, Jin, et al.
Published: (2024)

Federated Aggregation of Mallows Rankings: A Comparative Analysis of Borda and Lehmer Coding
by: Sima, Jin, et al.
Published: (2024)

Privacy-Preserving Retrieval-Augmented Generation with Differential Privacy
by: Koga, Tatsuki, et al.
Published: (2024)

Can We Infer Confidential Properties of Training Data from LLMs?
by: Huang, Pengrun, et al.
Published: (2025)

TS-Agent: Understanding and Reasoning Over Raw Time Series via Iterative Insight Gathering
by: Liu, Penghang, et al.
Published: (2025)

Optimal Stopping Methodology for the Secretary Problem with Random Queries
by: Moustakides, George V., et al.
Published: (2021)

Generalized Orthogonal de Bruijn and Kautz Sequences
by: Chen, Yuan-Pon, et al.
Published: (2025)

Reducing Data Fragmentation in Data Deduplication Systems via Partial Repetition and Coding
by: Li, Yun-Han, et al.
Published: (2024)

Is Gradient Ascent Really Necessary? Memorize to Forget for Machine Unlearning
by: Huang, Zhuo, et al.
Published: (2026)

Learning Scalable Structural Representations for Link Prediction with Bloom Signatures
by: Zhang, Tianyi, et al.
Published: (2023)

GraphMaker: Can Diffusion Models Generate Large Attributed Graphs?
by: Li, Mufei, et al.
Published: (2023)

Spatially-Coupled Network RNA Velocities: A Control-Theoretic Perspective
by: Hou, Boya, et al.
Published: (2026)

The Gapped $k$-Deck Problem
by: Golm, Jonas, et al.
Published: (2022)

Online Distribution Learning with Local Private Constraints
by: Sima, Jin, et al.
Published: (2024)

Langevin Unlearning: A New Perspective of Noisy Gradient Descent for Machine Unlearning
by: Chien, Eli, et al.
Published: (2024)

Data Redaction from Conditional Generative Models
by: Kong, Zhifeng, et al.
Published: (2023)

A Closer Look at the Learnability of Out-of-Distribution (OOD) Detection
by: Garov, Konstantin, et al.
Published: (2025)

Distribution Learning with Valid Outputs Beyond the Worst-Case
by: Rittler, Nick, et al.
Published: (2024)