Self-Recognition in Language Models

A rapidly growing number of applications rely on a small set of closed-source language models (LMs). This dependency might introduce novel security risks if LMs develop self-recognition capabilities. Inspired by human identity verification methods, we propose a novel approach for assessing self-reco...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2024-10
Hauptverfasser:	Davidson, Tim R, Surkov, Viacheslav, Veselovsky, Veniamin, Russo, Giuseppe, West, Robert, Gulcehre, Caglar
Format:	Artikel
Sprache:	eng
Schlagworte:	Recognition Security
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!