RapidUn: Influence-Driven Parameter Reweighting for Efficient Large Language Model Unlearning

arXiv:2512.04457 · cs.CL · Submitted 2025-12-04 · Read on arXiv

cs.CL

Submitted: 2025-12-04

Updated: 2026-09-24

Comments: Code available at: https://github.com/eyerf/RapidUn

Code: https://github.com/tatsu-lab/stanford_alpaca

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Perplexity — 15× in this paper · explained in 3 episodes
• Approximate Unlearning — 14× in this paper · explained in 1 episode
• Machine Unlearning — 14× in this paper · explained in 2 episodes
• Benchmark — 12× in this paper · explained in 2 episodes
• Ablation — 7× in this paper · explained in 1 episode
• Fine-Tuning — 6× in this paper · explained in 5 episodes
• Robustness — 6× in this paper · explained in 5 episodes
• Transformer — 6× in this paper · explained in 2 episodes
• Meeting of the Association for Computational Linguistics — 5× in this paper
• Influence Functions — 4× in this paper · explained in 2 episodes
• LoRA Adapters — 4× in this paper · explained in 3 episodes
• Symposium on Security and Privacy — 3× in this paper
• Accuracy — 2× in this paper · explained in 1 episode
• Adam — 2× in this paper · explained in 2 episodes
• Aggregation — 2× in this paper · explained in 1 episode
• Analyzer — 2× in this paper · explained in 1 episode
• International Conference on Learning Representations — 2× in this paper
• Large Language Models (LLMs) — 2× in this paper · explained in 6 episodes
• Parameter-Efficient Fine-Tuning — 2× in this paper · explained in 2 episodes
• Trace — 2× in this paper · explained in 2 episodes
• Transfer Learning — 2× in this paper · explained in 10 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Adversarial Examples — 1× in this paper · explained in 2 episodes
• Alignment — 1× in this paper · explained in 1 episode
• Attack Success Rate (ASR) — 1× in this paper · explained in 2 episodes
• Benchmarking — 1× in this paper · explained in 3 episodes
• Catastrophic Forgetting — 1× in this paper · explained in 5 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Generative AI — 1× in this paper · explained in 2 episodes
• In-Context Learning — 1× in this paper · explained in 4 episodes
• International Conference on Machine Learning — 1× in this paper
• Interpretability — 1× in this paper · explained in 15 episodes
• Pruning — 1× in this paper · explained in 4 episodes
• Sample Efficiency — 1× in this paper · explained in 4 episodes
• Steering — 1× in this paper · explained in 2 episodes
• Tokenization — 1× in this paper · explained in 2 episodes

Sources

• Extracting memorized pieces of (copyrighted) books from open-weight language models
• On Effects of Steering Latent Representation for Large Language Model Unlearning
• Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning
• Existing Large Language Model Unlearning Evaluations Are Inconclusive
• Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned
• Reference-Specific Unlearning Metrics Can Hide the Truth: A Reality Check
• RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models
• TOFU: A Task of Fictitious Unlearning for LLMs
• Mass-Editing Memory in a Transformer
• Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning
• LUME: LLM Unlearning with Multitask Evaluations
• Rethinking Machine Unlearning for Large Language Models
• BLUR: A Bi-Level Optimization Approach for LLM Unlearning
• SoK: Machine Unlearning for Large Language Models
• Concealed Data Poisoning Attacks on NLP Models
• Keeping an Eye on LLM Unlearning: The Hidden Risk and Remedy
• Machine Unlearning: A Survey
• BalDRO: A Distributionally Robust Optimization based Framework for Large Language Model Unlearning
• DeepClean: Machine Unlearning on the Cheap by Resetting Privacy Sensitive Weights using the Fisher Diagonal
• A Closer Look at Machine Unlearning for Large Language Models

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering