1 hasil untuk "Jonathan Stray"
Menampilkan 1–1 · 0,92 detik · RSS
-
Artikel Jurnal Teks lengkap
Summon a demon and bind it: A grounded theory of LLM red teaming
Engaging in the deliberate generation of abnormal outputs from Large Language Models (LLMs) by attacking them is a novel human activity. This paper presents a thorough exposition of how and why people perform such attacks, defining LLM red-teaming based on extensive and diverse evidence. Using a…