activity
20242026
most citedAn Investigation into the Performance of Non-Contrastive Self-Supervised Learning Methods for Network Intrusion Detection

2 citations · 5 across the 12 of their papers we have counts for

collaborators
Showing cs.AIShow all

1 paper · 1 filter

cs.AI2026

LLM Self-Recognition: Steering and Retrieving Activation Signatures

Thibaud Ardoin, Jonas Schäfer, Gerhard Wunder

Recent advances in interpretability suggest that large language models (LLMs) implicitly encode signals in their generated text that enable self-recognition of their outputs. We de…