arXiv Machine Learning
Storage Is Not Strategy: State-Conditioned Support Control for LLM Unlearning
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Computation and Language
Sep 15
When Edit Localization Amplifies Relative Selection Bias: Gradient Geometry, Target Mismatch, and Importance Weighting
arXiv:2609.13709v1 Announce Type: new Abstract: Human corrections identify editable spans, but the examples receiving corrections may come from a selective feedback channel. We analyze this interacti...
Hugging Face Trending Papers
Aug 13
Predictive Memory Localization: Forecasting Selective Intervention Paths from Internal Signals
Activation steering turns localized representations into control directions, but localization alone does not reveal whether a direction has a selective operating regime. We introduce Predictive Memory Localization (PML), which treats the measured-grid intervention path as the predictive object of memory localization.
arXiv AI
Aug 14
Predictive Memory Localization: Forecasting Selective Intervention Paths from Internal Signals
arXiv:2608. 12892v1 Announce Type: new Abstract: Activation steering turns localized representations into control directions, but localization alone does not reveal whether a direction has a selective operating regime.
arXiv AI
Aug 24
UpgradeBench: A Decision-Centric Benchmark for Upgrading Fine-Tuned LLM Specialists
UpgradeBench is a decision‑centric longitudinal benchmark that evaluates how fine‑tuned language‑model specialists should be handled when new base‑model releases occur. It covers four consecutive Qwen releases, a continuation checkpoint, six tasks, two model sizes, and OLMo checkpoints with known training lineage, and examines whether retraining, adapter transfer, or other recovery strategies improve specialist performance. The benchmark reveals that upgrade gains vary by task and release interval, that direct adapter copying is sensitive to pretraining distance, and that teacher relabeling can recover specialists without new annotations. "whyItMatters":"The study provides actionable insights into the cost‑effective management of specialist models across model releases, showing how to balance retraining effort with performance gains."
Hugging Face Trending Papers
Jun 9
Null-Space Constrained Low-Rank Adaptation for Response-Specified Large Language Model Unlearning
Large language model unlearning aims to suppress designated undesirable knowledge while preserving benign capabilities. Many unlearning objectives focus on suppressing undesired answers, while recent target-guided variants specify replacement behavior but still leave update locality largely unconstrained.
arXiv AI
Jun 10
Null-Space Constrained Low-Rank Adaptation for Response-Specified Large Language Model Unlearning
arXiv:2606. 10989v1 Announce Type: new Abstract: Large language model unlearning aims to suppress designated undesirable knowledge while preserving benign capabilities.