all AI news
Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned. (arXiv:2209.07858v2 [cs.CL] UPDATED)
Nov. 24, 2022, 7:18 a.m. | Deep Ganguli, Liane Lovitt, Jackson Kernion, Amanda Askell, Yuntao Bai, Saurav Kadavath, Ben Mann, Ethan Perez, Nicholas Schiefer, Kamal Ndousse, Andy
cs.CL updates on arXiv.org arxiv.org
We describe our early efforts to red team language models in order to
simultaneously discover, measure, and attempt to reduce their potentially
harmful outputs. We make three main contributions. First, we investigate
scaling behaviors for red teaming across 3 model sizes (2.7B, 13B, and 52B
parameters) and 4 model types: a plain language model (LM); an LM prompted to
be helpful, honest, and harmless; an LM with rejection sampling; and a model
trained to be helpful and harmless using reinforcement …
arxiv language language models lessons learned reduce scaling
More from arxiv.org / cs.CL updates on arXiv.org
Jobs in AI, ML, Big Data
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Lead Software Engineer - Artificial Intelligence, LLM
@ OpenText | Hyderabad, TG, IN
Lead Software Engineer- Python Data Engineer
@ JPMorgan Chase & Co. | GLASGOW, LANARKSHIRE, United Kingdom
Data Analyst (m/w/d)
@ Collaboration Betters The World | Berlin, Germany
Data Engineer, Quality Assurance
@ Informa Group Plc. | Boulder, CO, United States
Director, Data Science - Marketing
@ Dropbox | Remote - Canada