Cover Image

LLM Unlearning Reveals a Stronger-Than-Expected Coreset Effect in Current Benchmarks

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Pal, Soumyadeep, Wang, Changsheng, Diffenderfer, James, Kailkhura, Bhavya, Liu, Sijia
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

SOUL: Unlocking the Power of Second-Order Optimization for LLM Unlearning
by: Jia, Jinghan, et al.
Published: (2024)

UProp: Investigating the Uncertainty Propagation of LLMs in Multi-Step Agentic Decision-Making
by: Duan, Jinhao, et al.
Published: (2025)

LLM Unlearning Under the Microscope: A Full-Stack View on Methods and Metrics
by: Fan, Chongyu, et al.
Published: (2025)

Position: Zeroth-Order Optimization in Deep Learning Is Underexplored, Not Underpowered
by: Liu, Sijia, et al.
Published: (2026)

GTBench: Uncovering the Strategic Reasoning Limitations of LLMs via Game-Theoretic Evaluations
by: Duan, Jinhao, et al.
Published: (2024)

UPCORE: Utility-Preserving Coreset Selection for Balanced Unlearning
by: Patil, Vaidehi, et al.
Published: (2025)

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

Reveal and Release: Iterative LLM Unlearning with Self-generated Data
by: Xie, Linxi, et al.
Published: (2025)

Confident or Seek Stronger: Exploring Uncertainty-Based On-device LLM Routing From Benchmarking to Generalization
by: Chuang, Yu-Neng, et al.
Published: (2025)

Low-rank finetuning for LLMs: A fairness perspective
by: Das, Saswat, et al.
Published: (2024)

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

Shifting Attention to Relevance: Towards the Predictive Uncertainty Quantification of Free-Form Large Language Models
by: Duan, Jinhao, et al.
Published: (2023)

SEUF: Is Unlearning One Expert Enough for Mixture-of-Experts LLMs?
by: Zhuang, Haomin, et al.
Published: (2024)

Explainable LLM Unlearning Through Reasoning
by: Liao, Junfeng, et al.
Published: (2026)

Improving Robustness In Sparse Autoencoders via Masked Regularization
by: Narayanaswamy, Vivek, et al.
Published: (2026)

Backdoor Secrets Unveiled: Identifying Backdoor Data with Optimized Scaled Prediction Consistency
by: Pal, Soumyadeep, et al.
Published: (2024)

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

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

DRAGON: Guard LLM Unlearning in Context via Negative Detection and Reasoning
by: Wang, Yaxuan, et al.
Published: (2025)

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

End-to-End Mesh Optimization of a Hybrid Deep Learning Black-Box PDE Solver
by: Ma, Shaocong, et al.
Published: (2024)

RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models
by: Jin, Zhuoran, et al.
Published: (2024)

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

Benchmark Inflation: Revealing LLM Performance Gaps Using Retro-Holdouts
by: Haimes, Jacob, et al.
Published: (2024)

Unlearned but Not Forgotten: Data Extraction after Exact Unlearning in LLM
by: Wu, Xiaoyu, et al.
Published: (2025)

BOOM: Benchmarking Out-Of-distribution Molecular Property Predictions of Machine Learning Models
by: Antoniuk, Evan R., et al.
Published: (2025)

Harmonizing Multi-Objective LLM Unlearning via Unified Domain Representation and Bidirectional Logit Distillation
by: Zhong, Yisheng, et al.
Published: (2026)

Reverse Thinking Makes LLMs Stronger Reasoners
by: Chen, Justin Chih-Yao, et al.
Published: (2024)

Benchmarks Saturate When The Model Gets Smarter Than The Judge
by: Ballon, Marthe, et al.
Published: (2026)

Reasoning Model Unlearning: Forgetting Traces, Not Just Answers, While Preserving Reasoning Skills
by: Wang, Changsheng, et al.
Published: (2025)

Measuring the Depth of LLM Unlearning via Activation Patching
by: Lee, Jaeung, et al.
Published: (2026)

Teaching Pretrained Language Models to Think Deeper with Retrofitted Recurrence
by: McLeish, Sean, et al.
Published: (2025)

Mini-batch Coresets for Memory-efficient Language Model Training on Data Mixtures
by: Nguyen, Dang, et al.
Published: (2024)

TAGCOS: Task-agnostic Gradient Clustered Coreset Selection for Instruction Tuning Data
by: Zhang, Jipeng, et al.
Published: (2024)

Two Minds Better Than One: Collaborative Reward Modeling for LLM Alignment
by: Zhang, Jiazheng, et al.
Published: (2025)

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

Offset Unlearning for Large Language Models
by: Huang, James Y., et al.
Published: (2024)

Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts
by: Zheng, Haizhong, et al.
Published: (2025)

Debate Helps Weak Judges Reward Stronger Models
by: Elasky, Ethan, et al.
Published: (2026)

Generative Value Conflicts Reveal LLM Priorities
by: Liu, Andy, et al.
Published: (2025)