Cover Image

CURE: Controlled Unlearning for Robust Embeddings -- Mitigating Conceptual Shortcuts in Pre-Trained Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kocak, Aysenur, Yang, Shuo, Prenkaj, Bardh, Kasneci, Gjergji
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

RAZOR: Sharpening Knowledge by Cutting Bias with Unsupervised Text Rewriting
by: Yang, Shuo, et al.
Published: (2024)

Doubling Your Data in Minutes: Ultra-fast Tabular Data Generation via LLM-Induced Dependency Graphs
by: Yang, Shuo, et al.
Published: (2025)

Active Tabular Augmentation via Policy-Guided Diffusion Inpainting
by: Zhang, Zheyu, et al.
Published: (2026)

SCISSOR: Mitigating Semantic Bias through Cluster-Aware Siamese Networks for Robust Classification
by: Yang, Shuo, et al.
Published: (2025)

From Confidence to Collapse in LLM Factual Robustness
by: Fastowski, Alina, et al.
Published: (2025)

Probabilistic Aggregation and Targeted Embedding Optimization for Collective Moral Reasoning in Large Language Models
by: Yuan, Chenchen, et al.
Published: (2025)

Not All Features Deserve Attention: Graph-Guided Dependency Learning for Tabular Data Generation with Language Models
by: Zhang, Zheyu, et al.
Published: (2025)

Reinforcement Unlearning via Group Relative Policy Optimization
by: Zaradoukas, Efstratios, et al.
Published: (2026)

Injecting Falsehoods: Adversarial Man-in-the-Middle Attacks Undermining Factual Recall in LLMs
by: Fastowski, Alina, et al.
Published: (2025)

Is Crowdsourcing Breaking Your Bank? Cost-Effective Fine-Tuning of Pre-trained Language Models with Proximal Policy Optimization
by: Yang, Shuo, et al.
Published: (2024)

SAGE: Sparse Adaptive Guidance for Dependency-Aware Tabular Data Generation
by: Yang, Shuo, et al.
Published: (2026)

Graph Inverse Style Transfer for Counterfactual Explainability
by: Prenkaj, Bardh, et al.
Published: (2025)

Position: Uncertainty Quantification Needs Reassessment for Large-language Model Agents
by: Kirchhof, Michael, et al.
Published: (2025)

Emergent Abilities in Large Language Models: A Survey
by: Berti, Leonardo, et al.
Published: (2025)

Enriching Tabular Data with Contextual LLM Embeddings: A Comprehensive Ablation Study for Ensemble Classifiers
by: Kasneci, Gjergji, et al.
Published: (2024)

Moral Lenses, Political Coordinates: Towards Ideological Positioning of Morally Conditioned LLMs
by: Yuan, Chenchen, et al.
Published: (2026)

TabSCM: A practical Framework for Generating Realistic Tabular Data
by: Jacob, Sven, et al.
Published: (2026)

Towards Non-Adversarial Algorithmic Recourse
by: Leemann, Tobias, et al.
Published: (2024)

Where Paths Split: Localized, Calibrated Control of Moral Reasoning in Large Language Models
by: Yuan, Chenchen, et al.
Published: (2026)

Attention Mechanisms Don't Learn Additive Models: Rethinking Feature Importance for Transformers
by: Leemann, Tobias, et al.
Published: (2024)

Consolidating Rewarded Perturbations for LLM Post-Training
by: Zhang, Zheyu, et al.
Published: (2026)

EvalxNLP: A Framework for Benchmarking Post-Hoc Explainability Methods on NLP Models
by: Dhaini, Mahdi, et al.
Published: (2025)

CURE:Circuit-Aware Unlearning for LLM-based Recommendation
by: Chen, Ziheng, et al.
Published: (2026)

Gender Bias in Explainability: Investigating Performance Disparity in Post-hoc Methods
by: Dhaini, Mahdi, et al.
Published: (2025)

Robust Stochastic Graph Generator for Counterfactual Explanations
by: Prado-Romero, Mario Alfonso, et al.
Published: (2023)

Large Language Model Unlearning via Embedding-Corrupted Prompts
by: Liu, Chris Yuhao, et al.
Published: (2024)

TRADES: Generating Realistic Market Simulations with Diffusion Models
by: Berti, Leonardo, et al.
Published: (2025)

TLOB: A Novel Transformer Model with Dual Attention for Price Trend Prediction with Limit Order Book Data
by: Berti, Leonardo, et al.
Published: (2025)

Large Language Model Unlearning
by: Yao, Yuanshun, et al.
Published: (2023)

Machine Unlearning of Pre-trained Large Language Models
by: Yao, Jin, et al.
Published: (2024)

ZeroUnlearn: Few-Shot Knowledge Unlearning in Large Language Models
by: Lin, Yujie, et al.
Published: (2026)

Outlier-Safe Pre-Training for Robust 4-Bit Quantization of Large Language Models
by: Park, Jungwoo, et al.
Published: (2025)

Learning Shortcuts: On the Misleading Promise of NLU in Language Models
by: Bihani, Geetanjali, et al.
Published: (2024)

A Survey on Graph Counterfactual Explanations: Definitions, Methods, Evaluation, and Research Challenges
by: Prado-Romero, Mario Alfonso, et al.
Published: (2022)

Robust LLM Unlearning with MUDMAN: Meta-Unlearning with Disruption Masking And Normalization
by: Sondej, Filip, et al.
Published: (2025)

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

Towards Robust Knowledge Unlearning: An Adversarial Framework for Assessing and Improving Unlearning Robustness in Large Language Models
by: Yuan, Hongbang, et al.
Published: (2024)

Understanding Knowledge Drift in LLMs through Misinformation
by: Fastowski, Alina, et al.
Published: (2024)

Memory-efficient Energy-adaptive Inference of Pre-Trained Models on Batteryless Embedded Systems
by: Farina, Pietro, et al.
Published: (2024)

Learn while Unlearn: An Iterative Unlearning Framework for Generative Language Models
by: Tang, Haoyu, et al.
Published: (2024)