Siirry offline-tilaan Player FM avulla!
[QA] Mission Impossible: A Statistical Perspective on Jailbreaking LLMs
Manage episode 432612331 series 3524393
This paper analyzes preference alignment and jailbreaking in large language models, proposing E-RLHF as a cost-effective method to enhance safety without compromising performance.
https://arxiv.org/abs//2408.01420
YouTube: https://www.youtube.com/@ArxivPapers
TikTok: https://www.tiktok.com/@arxiv_papers
Apple Podcasts: https://podcasts.apple.com/us/podcast/arxiv-papers/id1692476016
Spotify: https://podcasters.spotify.com/pod/show/arxiv-papers
--- Support this podcast: https://podcasters.spotify.com/pod/show/arxiv-papers/support
1619 jaksoa
Manage episode 432612331 series 3524393
This paper analyzes preference alignment and jailbreaking in large language models, proposing E-RLHF as a cost-effective method to enhance safety without compromising performance.
https://arxiv.org/abs//2408.01420
YouTube: https://www.youtube.com/@ArxivPapers
TikTok: https://www.tiktok.com/@arxiv_papers
Apple Podcasts: https://podcasts.apple.com/us/podcast/arxiv-papers/id1692476016
Spotify: https://podcasters.spotify.com/pod/show/arxiv-papers
--- Support this podcast: https://podcasters.spotify.com/pod/show/arxiv-papers/support
1619 jaksoa
כל הפרקים
×Tervetuloa Player FM:n!
Player FM skannaa verkkoa löytääkseen korkealaatuisia podcasteja, joista voit nauttia juuri nyt. Se on paras podcast-sovellus ja toimii Androidilla, iPhonela, ja verkossa. Rekisteröidy sykronoidaksesi tilaukset laitteiden välillä.