all AI news
Measuring and Controlling Persona Drift in Language Model Dialogs
Feb. 20, 2024, 5:43 a.m. | Kenneth Li, Tianle Liu, Naomi Bashkansky, David Bau, Fernanda Vi\'egas, Hanspeter Pfister, Martin Wattenberg
cs.LG updates on arXiv.org arxiv.org
Abstract: Prompting is a standard tool for customizing language-model chatbots, enabling them to take on a specific "persona". An implicit assumption in the use of prompts is that they will be stable, so the chatbot will continue to generate text according to the stipulated persona for the duration of a conversation. We propose a quantitative benchmark to test this assumption, evaluating persona stability via self-chats between two personalized chatbots. Testing popular models like LLaMA2-chat-70B, we reveal …
abstract arxiv chatbot chatbots cs.ai cs.cl cs.lg drift enabling generate language language model measuring prompting prompts standard text them tool type will
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
AI Research Scientist
@ Vara | Berlin, Germany and Remote
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
AI Engineering Manager
@ M47 Labs | Barcelona, Catalunya [Cataluña], Spain