Przejdź do trybu offline z Player FM !
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
1081 odcinków
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
1081 odcinków
Alle episoder
×Zapraszamy w Player FM
Odtwarzacz FM skanuje sieć w poszukiwaniu wysokiej jakości podcastów, abyś mógł się nią cieszyć już teraz. To najlepsza aplikacja do podcastów, działająca na Androidzie, iPhonie i Internecie. Zarejestruj się, aby zsynchronizować subskrypcje na różnych urządzeniach.