RESEARCHMonitorWATCHLIST
PreUnlearn: Auditing Collateral Knowledge Damage Before Large Language Model Unlearning
arXiv cs.CL — Computation and Language
Factual evidence
What the source reports
Researchers introduced PreUnlearn, a method to measure collateral knowledge damage and information propagation during LLM unlearning.
Inspect the evidence
- Inclusion basis
- Enterprise AI
- Publisher and source type
- arXiv cs.CL — Computation and Language · RESEARCH
- Published by source
- 23 September 2026
- Collected by OneBench
- 24 Sept 2026, 03:01 UK
Stored source excerpt
arXiv:2606.18473v2 Announce Type: replace Abstract: Machine unlearning for large language models (LLMs) aims to remove specified knowledge while preserving the rest of the model's capabilities.…
Short excerpt from the collected text, not the full source. Use the source link to read it in context.
The factual summary is a OneBench synthesis, not a quotation or independent verification. Collection time is not publication time. Open the source for its full context; related reporting can share the same underlying announcement.