Routing-Aware Expert Calibration for Machine Unlearning in Mixture-of-Experts Language Models

arXiv:2606.10338 · cs.CL, cs.AI · Submitted 2026-06-09 · Read on arXiv

cs.CL, cs.AI

Submitted: 2026-06-09

Updated: 2026-09-23

Terminology

• Trace — 73× in this paper · explained in 2 episodes
• Regularization — 22× in this paper · explained in 3 episodes
• Benchmark — 12× in this paper · explained in 2 episodes
• Calibration — 11× in this paper · explained in 7 episodes
• Machine Unlearning — 10× in this paper · explained in 2 episodes
• Accuracy — 6× in this paper · explained in 1 episode
• Ablation — 5× in this paper · explained in 1 episode
• Ablation study — 3× in this paper · explained in 1 episode
• Negative Preference Optimization — 3× in this paper
• Transformer — 3× in this paper · explained in 2 episodes
• EMMA — 2× in this paper · explained in 2 episodes
• Fine-Tuning — 2× in this paper · explained in 5 episodes
• General Data Protection Regulation — 2× in this paper
• Mixture-of-Experts (MoE) — 2× in this paper · explained in 7 episodes
• Transformer Models — 2× in this paper · explained in 2 episodes
• Adam — 1× in this paper · explained in 2 episodes
• Alignment — 1× in this paper · explained in 1 episode
• Approximate Unlearning — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 4 episodes
• California Consumer Privacy Act — 1× in this paper
• Continual Learning — 1× in this paper · explained in 2 episodes
• In-Context Learning — 1× in this paper · explained in 4 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Sparsity — 1× in this paper · explained in 4 episodes
• Two-Stage Framework — 1× in this paper · explained in 2 episodes

Sources

• Measuring Massive Multitask Language Understanding
• To Each (Textual Sequence) Its Own: Improving Memorized-Data Unlearning in Large Language Models
• WAGLE: Strategic Weight Attribution for Effective and Modular Unlearning in Large Language Models
• Unlearn What You Want to Forget: Efficient Unlearning for LLMs
• Mixtral of Experts
• DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
• RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models
• DeepSeek-V3 Technical Report
• GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding
• GLaM: Efficient Scaling of Language Models with Mixture-of-Experts
• The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning
• Who's Harry Potter? Approximate Unlearning in LLMs
• Continual Learning and Private Unlearning
• Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning
• Large Language Model Unlearning via Embedding-Corrupted Prompts
• KUDA: Knowledge Unlearning by Deviating Representation for Large Language Models
• Rethinking Machine Unlearning for Large Language Models
• Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity
• A Comprehensive Survey of Machine Unlearning Techniques for Large Language Models
• Quark: Controllable Text Generation with Reinforced Unlearning

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