PPU-Bench is a real-world benchmark exposing forget-retain trade-offs in MLLM unlearning and motivating Boundary-Aware Optimization to enforce intra-subject factual boundaries.
Towards safer large language models through machine unlearning
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
roles
background 3polarities
background 3representative citing papers
Machine unlearning conflates reversing the influence of specific training examples (untraining) with removing the full underlying distribution or behavior (unlearning).
ASRU combines activation redirection and reward-optimized fine-tuning to unlearn cross-modal sensitive knowledge in MLLMs, reporting +24.6% better unlearning effectiveness and 5.8x higher generation quality on Qwen3-VL while preserving utility with limited retained data.
A contrastive visual forgetting technique constrained to the null space of retained knowledge enables targeted unlearning of visual concepts in MLLMs while preserving non-target visual and all textual knowledge.
REGLU guides LoRA-based unlearning via representation subspaces and orthogonal regularization to outperform prior methods on forget-retain trade-off in LLM benchmarks.
MAGE builds a memory graph from a user anchor to generate its own supervision signals for corpus-free unlearning, matching the effectiveness of methods that use external reference data on TOFU and RWKU benchmarks.
The paper introduces a new taxonomy for model merging methods and reviews their applications in LLMs, MLLMs, continual learning, multi-task learning, and other subfields while outlining open challenges.
A survey classifying machine unlearning into centralized (exact and approximate), distributed/irregular data, verification, and privacy/security categories with technique overviews.
citing papers explorer
-
PPU-Bench:Real World Benchmark for Personalized Partial Unlearning in Vision Language Models
PPU-Bench is a real-world benchmark exposing forget-retain trade-offs in MLLM unlearning and motivating Boundary-Aware Optimization to enforce intra-subject factual boundaries.
-
Is your algorithm unlearning or untraining?
Machine unlearning conflates reversing the influence of specific training examples (untraining) with removing the full underlying distribution or behavior (unlearning).
-
ASRU: Activation Steering Meets Reinforcement Unlearning for Multimodal Large Language Models
ASRU combines activation redirection and reward-optimized fine-tuning to unlearn cross-modal sensitive knowledge in MLLMs, reporting +24.6% better unlearning effectiveness and 5.8x higher generation quality on Qwen3-VL while preserving utility with limited retained data.
-
Null Space Constrained Contrastive Visual Forgetting for MLLM Unlearning
A contrastive visual forgetting technique constrained to the null space of retained knowledge enables targeted unlearning of visual concepts in MLLMs while preserving non-target visual and all textual knowledge.
-
Representation-Guided Parameter-Efficient LLM Unlearning
REGLU guides LoRA-based unlearning via representation subspaces and orthogonal regularization to outperform prior methods on forget-retain trade-off in LLM benchmarks.
-
From Anchors to Supervision: Memory-Graph Guided Corpus-Free Unlearning for Large Language Models
MAGE builds a memory graph from a user anchor to generate its own supervision signals for corpus-free unlearning, matching the effectiveness of methods that use external reference data on TOFU and RWKU benchmarks.
-
Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities
The paper introduces a new taxonomy for model merging methods and reviews their applications in LLMs, MLLMs, continual learning, multi-task learning, and other subfields while outlining open challenges.
-
Machine Unlearning: A Comprehensive Survey
A survey classifying machine unlearning into centralized (exact and approximate), distributed/irregular data, verification, and privacy/security categories with technique overviews.