Lépjen offline állapotba az Player FM alkalmazással!
Poser: Unmasking Alignment Faking LLMs by Manipulating Their Internals
Manage episode 417498420 series 3524393
Large Language Models (LLMs) can deceive as 'alignment fakers.' A benchmark with 324 LLM pairs is introduced to detect misbehaving models, achieving 98% accuracy with a specific strategy.
https://arxiv.org/abs//2405.05466
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
1087 epizódok
Manage episode 417498420 series 3524393
Large Language Models (LLMs) can deceive as 'alignment fakers.' A benchmark with 324 LLM pairs is introduced to detect misbehaving models, achieving 98% accuracy with a specific strategy.
https://arxiv.org/abs//2405.05466
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
1087 epizódok
Minden epizód
×Üdvözlünk a Player FM-nél!
A Player FM lejátszó az internetet böngészi a kiváló minőségű podcastok után, hogy ön élvezhesse azokat. Ez a legjobb podcast-alkalmazás, Androidon, iPhone-on és a weben is működik. Jelentkezzen be az feliratkozások szinkronizálásához az eszközök között.