arXiv (All)open access
Measuring the Depth of LLM Unlearning via Activation Patching
computation and language, artificial intelligence, machine learning
This document is indexed with metadata only — full text is not available in the archive for this record.
Open the official source ↗Related documents
Record · ID 793684
Retrieved via
Conceptio — every document is proof-bundled with source, license, and retrieval metadata.