October 20, 2023 front

ML Newsnew | past | best | rss | submit

Stories from October 20, 2023 (UTC)

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

1.	Beyond Memorization: Violating Privacy via Inference with Large Language Models (arxiv.org)
	2 points by omarfarooq on Oct 20, 2023 \| hide \| past \| pdf \| discuss
2.	GPT-4 Doesn't Know It's Wrong (arxiv.org)
	2 points by belter on Oct 20, 2023 \| hide \| past \| pdf \| discuss
3.	Prompt Injection Attacks and Defenses in LLM-Integrated Applications (arxiv.org)
	1 point by belter on Oct 20, 2023 \| hide \| past \| pdf \| discuss
4.	Revealing the structure of language model capabilities (arxiv.org)
	1 point by famouswaffles on Oct 20, 2023 \| hide \| past \| pdf \| discuss