February 27, 2024 front

ML Newsnew | past | best | rss | submit

Stories from February 27, 2024 (UTC)

Go back a day, month, or year. Go forward a day.

1.	Defending LLMs against Jailbreaking Attacks via Backtranslation (arxiv.org)
	67 points by saliagato on Feb 27, 2024 \| hide \| past \| pdf \| 48 comments
2.	SPML: A DSL for Defending LLMs Against Prompt Attacks (arxiv.org)
	6 points by reshabh on Feb 27, 2024 \| hide \| past \| pdf \| 2 comments
3.	Nemotron-4 15B large multilingual language model trained on 8T tokens (arxiv.org)
	3 points by hack_ml on Feb 27, 2024 \| hide \| past \| pdf \| 1 comment
4.	Genie: Generative Interactive Environments (arxiv.org)
	2 points by jonbaer on Feb 27, 2024 \| hide \| past \| pdf \| discuss
5.	ReWOO: Decoupling Reasoning from Observations for Efficient Augmented LMs (2023) (arxiv.org)
	2 points by CharlesW on Feb 27, 2024 \| hide \| past \| pdf \| discuss
6.	Turn Waste into Worth: Rectifying Top-$K$ Router of Moe (arxiv.org)
	1 point by PaulHoule on Feb 27, 2024 \| hide \| past \| pdf \| discuss
7.	A Survey on Data Selection for Language Models (arxiv.org)
	1 point by sebg on Feb 27, 2024 \| hide \| past \| pdf \| discuss
8.	How Do Humans Write Code? Large Models Do It the Same Way Too (arxiv.org)
	1 point by saliagato on Feb 27, 2024 \| hide \| past \| pdf \| discuss
9.	Genie: Generative Interactive Environments (arxiv.org)
	1 point by reqo on Feb 27, 2024 \| hide \| past \| pdf \| discuss