:: Library Catalog

Cover Image

Saved in:

Bibliographic Details
Main Authors:	Qian, Timothy, Suriyakumar, Vinith, Wilson, Ashia, Hadfield-Menell, Dylan
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	https://arxiv.org/abs/2505.09500
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

UCD: Unlearning in LLMs via Contrastive Decoding
by: Suriyakumar, Vinith M., et al.
Published: (2025)

Unstable Unlearning: The Hidden Risk of Concept Resurgence in Diffusion Models
by: Suriyakumar, Vinith M., et al.
Published: (2024)

Defending Against Unforeseen Failure Modes with Latent Adversarial Training
by: Casper, Stephen, et al.
Published: (2024)

Algorithmic Pluralism: A Structural Approach To Equal Opportunity
by: Jain, Shomik, et al.
Published: (2023)

Distributional Process Reward Models: Calibrated Prediction of Future Rewards via Conditional Optimal Transport
by: Ma, Rachel, et al.
Published: (2026)

Distributional Preference Learning: Understanding and Accounting for Hidden Context in RLHF
by: Siththaranjan, Anand, et al.
Published: (2023)

Evaluation without Generation: Non-Generative Assessment of Harmful Model Specialization with Applications to CSAM
by: Suriyakumar, Vinith M., et al.
Published: (2026)

Alignment Tampering: How Reinforcement Learning from Human Feedback Is Exploited to Optimize Misaligned Biases
by: Hahm, Dongyoon, et al.
Published: (2026)

Goal Inference from Open-Ended Dialog
by: Ma, Rachel, et al.
Published: (2024)

Flexible Agent Alignment with Goal Inference from Open-Ended Dialog
by: Ma, Rachel, et al.
Published: (2025)

Activation Steering via Generative Causal Mediation
by: Sankaranarayanan, Aruna, et al.
Published: (2026)

Unlearning or Obfuscating? Jogging the Memory of Unlearned LLMs via Benign Relearning
by: Hu, Shengyuan, et al.
Published: (2024)

When Style Breaks Safety: Defending LLMs Against Superficial Style Alignment
by: Xiao, Yuxin, et al.
Published: (2025)

Unlearning's Blind Spots: Over-Unlearning and Prototypical Relearning Attack
by: Ha, SeungBum, et al.
Published: (2025)

Meta-Unlearning on Diffusion Models: Preventing Relearning Unlearned Concepts
by: Gao, Hongcheng, et al.
Published: (2024)

Efficient Unlearning through Maximizing Relearning Convergence Delay
by: Tran, Khoa, et al.
Published: (2026)

Rethinking Benign Relearning: Syntax as the Hidden Driver of Unlearning Failures
by: Yoon, Sangyeon, et al.
Published: (2026)

One-shot Empirical Privacy Estimation for Federated Learning
by: Andrew, Galen, et al.
Published: (2023)

FedCARE: Federated Unlearning with Conflict-Aware Projection and Relearning-Resistant Recovery
by: Li, Yue, et al.
Published: (2026)

Position: AI Evaluations Should be Grounded on a Theory of Capability
by: Jo, Nathanael, et al.
Published: (2025)

Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs
by: Sheshadri, Abhay, et al.
Published: (2024)

COLUR: Confidence-Oriented Learning, Unlearning and Relearning with Noisy-Label Data for Model Restoration and Refinement
by: Sui, Zhihao, et al.
Published: (2025)

Mean-field underdamped Langevin dynamics and its spacetime discretization
by: Fu, Qiang, et al.
Published: (2023)

Unlearn to Relearn Backdoors: Deferred Backdoor Functionality Attacks on Deep Learning Models
by: Shin, Jeongjin, et al.
Published: (2024)

The Approximate Fisher Influence Function: Faster Estimation of Data Influence in Statistical Models
by: Lev, Omri, et al.
Published: (2024)

Efficient and accurate steering of Large Language Models through attention-guided feature learning
by: Davarmanesh, Parmida, et al.
Published: (2026)

Eight Methods to Evaluate Robust Unlearning in LLMs
by: Lynch, Aengus, et al.
Published: (2024)

Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond
by: Fan, Chongyu, et al.
Published: (2025)

Semivalue-based data valuation is arbitrary and gameable
by: Diehl, Hannah, et al.
Published: (2025)

High-accuracy sampling from constrained spaces with the Metropolis-adjusted Preconditioned Langevin Algorithm
by: Srinivasan, Vishwak, et al.
Published: (2024)

From Cross-Validation to SURE: Asymptotic Risk of Tuned Regularized Estimators
by: Adusumilli, Karun, et al.
Published: (2026)

Revisiting the Role of Relearning in Semantic Dementia
by: Jarvis, Devon, et al.
Published: (2025)

Fast sampling from constrained spaces using the Metropolis-adjusted Mirror Langevin algorithm
by: Srinivasan, Vishwak, et al.
Published: (2023)

Adaptive Kernel Selection for Stein Variational Gradient Descent
by: Melcher, Moritz, et al.
Published: (2025)

Randomness, Not Representation: The Unreliability of Evaluating Cultural Alignment in LLMs
by: Khan, Ariba, et al.
Published: (2025)

CALMA: A Process for Deriving Context-aligned Axes for Language Model Alignment
by: Soni, Prajna, et al.
Published: (2025)

Disjoint Processing Mechanisms of Hierarchical and Linear Grammars in Large Language Models
by: Sankaranarayanan, Aruna, et al.
Published: (2025)

Pitfalls of Evidence-Based AI Policy
by: Casper, Stephen, et al.
Published: (2025)

Prompt Injection as Role Confusion
by: Ye, Charles, et al.
Published: (2026)

Adaptive Backtracking Line Search
by: Cavalcanti, Joao V., et al.
Published: (2024)