We have no position on which of these two goals is better or more desirable—it likely depends on the task and the context—but we do find we can easily steer models towards distinct goals by simply asking for different kinds of behavior.
LLMS
-
Steering Language Models Away From Gender Stereotypes in Occupations
By
–
We look at the Winogender benchmark and show we can steer larger models towards two different goals: to output pronouns that are correlated with occupational gender statistics from the U.S. Bureau of Labor Statistics (red) or to move away from using stereotypical pronouns (green)
-
Larger Language Models Show More Bias on BBQ Benchmark
By
–
First, we find larger LMs are more biased on the BBQ benchmark. Prompting models to avoid bias by giving them instructions (IF) and asking for reasoning (CoT) reverses the trend but only for the largest models and only with enough RLHF training! (Darker lines = more RLHF)
-
Prompting Techniques Reduce Harmful Biases in Large Language Models
By
–
Language models (LMs) exhibit harmful biases that can get worse with size. Reinforcement learning from human feedback (RLHF) helps, but not always enough. We show that simple prompting approaches can help LMs trained with RLHF produce less harmful outputs. https://
arxiv.org/abs/2302.07459 -
AI Rapidly Transforming Programming and Software Development
By
–
A sign of our times is seeing how AI permeates every single productive sector at a very rapid pace. PROGRAMMING will be no exception. And as an example, here's a combo of content from these programming cracks, where AI is increasingly the star
-
Bing’s Chained Search Lookups: An Illustrative Example
By
–
Example illustrating Bing's apparent ability to do chained sequences of search lookups:
-
Large Language Models Accelerate AIOps Operations
By
–
How Large Language Models Like #ChatGPT Accelerate #AIOps via @forbes https://
forbes.com/sites/janakira
mmsv/2023/02/14/how-large-language-models-like-chatgpt-accelerate-aiops/
… -
ChatGPT Explained: How It Works and Why
By
–
What Is #ChatGPT Doing … and Why Does It Work? A detailed explanation by @stephen_wolfram #AI #RuleoftheRobots https://
writings.stephenwolfram.com/2023/02/what-i
s-chatgpt-doing-and-why-does-it-work/
… -
ChatGPT: Beauty Without Truth Yet
By
–
ChatGPT is a fight between Satya (Truth) and Sunder (Beauty). It is Sunder, but not Satya yet.
-
Google Incentivizes Employees for RLHF Bard Development
By
–
Google is offering an internal badge to their employees who help RLHF Bard. And slowly, RLHF will eat the world