Dossier
Alignment Whack-a-Mole Code
Coverage of Alignment Whack-a-Mole Code in the Nexus archive.
- Finetuning Activates Verbatim Recall of Copyrighted Books in LLMs
A study from the Alignment Whack-a-Mole Code project reveals that fine-tuning large language models (LLMs) can activate verbatim recall of copyrighted books, raising concerns about intellectual property compliance. The findings highlight potential risks in model training processes that may inadvertently reproduce protected content.