Stress-Testing Capability Elicitation With Password-Locked Models

To determine the safety of large language models (LLMs), AI developers must be able to assess their dangerous capabilities. But simple prompting strategies often fail to elicit an LLM's full capabilities. One way to elicit capabilities more robustly is to fine-tune the LLM to complete the task....

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Greenblatt, Ryan, Roger, Fabien, Krasheninnikov, Dmitrii, Krueger, David
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Computation and Language Computer Science - Learning
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!