CoVUBench is the first benchmark framework for evaluating multimodal copyright unlearning in LVLMs via synthetic data, systematic variations, and a dual protocol for forgetting efficacy and utility preservation.
First Conference on Language Modeling , year=
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
years
2026 6representative citing papers
GUARD-IT performs machine unlearning in LLMs via input-dependent activation steering at inference time, matching or exceeding gradient-based baselines on TOFU and MUSE while preserving utility and working under quantization.
CAP is a reinforcement-learning-driven prompt optimization framework that suppresses target knowledge in LLMs while preserving general capabilities, enabling reversible unlearning without any parameter updates.
ETW uses predictive entropy as a proxy for token informativeness to improve selective unlearning in LLMs, achieving better forgetting with less utility loss than prior token-level methods.
REGLU guides LoRA-based unlearning via representation subspaces and orthogonal regularization to outperform prior methods on forget-retain trade-off in LLM benchmarks.
citing papers explorer
-
Erase Persona, Forget Lore: Benchmarking Multimodal Copyright Unlearning in Large Vision Language Models
CoVUBench is the first benchmark framework for evaluating multimodal copyright unlearning in LVLMs via synthetic data, systematic variations, and a dual protocol for forgetting efficacy and utility preservation.
-
Inference-Time Machine Unlearning via Gated Activation Redirection
GUARD-IT performs machine unlearning in LLMs via input-dependent activation steering at inference time, matching or exceeding gradient-based baselines on TOFU and MUSE while preserving utility and working under quantization.
-
CAP: Controllable Alignment Prompting for Unlearning in LLMs
CAP is a reinforcement-learning-driven prompt optimization framework that suppresses target knowledge in LLMs while preserving general capabilities, enabling reversible unlearning without any parameter updates.
-
Forget What Matters, Keep the Rest: Selective Unlearning of Informative Tokens
ETW uses predictive entropy as a proxy for token informativeness to improve selective unlearning in LLMs, achieving better forgetting with less utility loss than prior token-level methods.
-
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.
- Less is More: Geometric Unlearning for LLMs with Minimal Data Disclosure