LLM Digest

Story

arxiv_cs_cl · Oct 29, 2026 · paper

Source brief

Preserving Utility in Continual LLM Unlearning via Orthogonal Projections

arxiv.orgOct 29, 2026
original source linked

In brief

Unlearning concerns the task of removing the influence of a sensitive portion of the training data, such as protected, copyrighted or private text, from a model without retraining it from scratch. While unlearning req...

Read the original at arxiv.org →Open in live feed Read that day’s brief

Preserving Utility in Continual LLM Unlearning via Orthogonal Projections

Earlier in this thread 4 items

Routed Continual Learning

CAMR: Compatibility-Aware Memory Replay for Continual Learning in Large Language Models

Continual Learning Exam: Benchmarking Long-Horizon RSI and Experiential Learning in LLM Agents

From Structured Records to Patient Narratives: Preserving Clinical Alignment in LLM-Generated Health Summaries