Hello everyone, Given the recent change in schedule, I'd like to send this quick reminder that the alignment reading group is meeting in one hour. Join Zoom Meeting https://oregonstate.zoom.us/j/95843260079?pwd=TzZTN0xPaFZrazRGTElud0J1cnJLUT... Password: 961594 Phone Dial-In Information +1 971 247 1195 US (Portland) +1 253 215 8782 US (Tacoma) +1 301 715 8592 US (Washington DC) Meeting ID: 958 4326 0079 All the best, Quintin On Thu, Feb 17, 2022 at 11:42 PM Pope, Quintin <popeq@oregonstate.edu> wrote:
Hello everyone,
I've looked at the survey results. Unfortunately, there's no timeslot that everyone can make. I've chosen Friday at 1 PM PST as the least conflicted meeting time. I hope to see everyone soon!
Our discussion paper will be "Red Teaming Language Models with Language Models <https://www.deepmind.com/research/publications/2022/Red-Teaming-Language-Models-with-Language-Models> ":
Language Models (LMs) often cannot be deployed because of their potential
to harm users in ways that are hard to predict in advance. Prior work identifies harmful behaviors before deployment by using human annotators to hand-write test cases. However, human annotation is expensive, limiting the number and diversity of test cases. In this work, we automatically find cases where a target LM behaves in a harmful way, by generating test cases (“red teaming”) using another LM. We evaluate the target LM’s replies to generated test questions using a classifier trained to detect offensive content, uncovering tens of thousands of offensive replies in a 280B parameter LM chatbot. We explore several methods, from zero-shot generation to reinforcement learning, for generating test cases with varying levels of diversity and difficulty. Furthermore, we use prompt engineering to control LM-generated test cases to uncover a variety of other harms, automatically finding groups of people that the chatbot discusses in offensive ways, personal and hospital phone numbers generated as the chatbot’s own contact info, leakage of private training data in generated text, and harms that occur over the course of a conversation. Overall, LM-based red teaming is one promising tool (among many needed) for finding and fixing diverse, undesirable LM behaviors before impacting users.
Join Zoom Meeting
https://oregonstate.zoom.us/j/95843260079?pwd=TzZTN0xPaFZrazRGTElud0J1cnJLUT...
Password: 961594
Phone Dial-In Information +1 971 247 1195 US (Portland) +1 253 215 8782 US (Tacoma) +1 301 715 8592 US (Washington DC)
Meeting ID: 958 4326 0079
All the best, Quintin