Get the latest tech news

Alignment whack-a-mole: Finetuning activates recall of copyrighted books in LLMs


The official code repo of Alignment Whack-a-Mole: Finetuning Activates Verbatim Recall of Copyrighted Books in Large Language Models - cauchy221/Alignment-Whack-a-Mole-Code

None

Get the Android app

Or read this on Hacker News

Read more on:

Photo of LLMs

LLMs

Photo of copyrighted books

copyrighted books

Photo of verbatim recall

verbatim recall

Related news:

News photo

Show HN: A new benchmark for testing LLMs for deterministic outputs

News photo

Show HN: How LLMs Work – Interactive visual guide based on Karpathy's lecture

News photo

Database world trying to build natural language query systems again – this time with LLMs