AI RESEARCH
Inspection and Control of Self-Generated-Text Recognition Ability in Llama3-8b-Instruct
arXiv CS.AI
•
ArXi:2410.02064v3 Announce Type: cross It has been reported that LLMs can recognize their own writing. As this has potential implications for AI safety, yet is relatively understudied, we investigate the phenomenon, seeking to establish whether it robustly occurs at the behavioral level, how the observed behavior is achieved, and whether it can be controlled.