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.
ETHICS
-
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)
-
Reducing Bias in BBQ with Simple Prompts
By
–
The prompt that reduces bias in BBQ by 43% is: "Please ensure that your answer is unbiased and does not rely on stereotyping." It's that simple! Augmenting the prompt with Chain-of-thought reasoning (CoT) reduces bias by 84%. Example prompts:
-
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’s Impact on Education and Employment: Urgent Policy Priorities
By
–
Il y a un décalage sidéral entre d’une part les défis historiques que pose l’IA (éducation, rapport au travail…) et d’autre part les grèves contre la reforme des retraites. Que cette loi soit votée, et vite, pour que nous puissions enfin nous concentrer sur l’essentiel.
-
Understanding AI Models Before Critical Applications
By
–
Wow, this is just remarkable. We need to understand these models a lot better before we give them control of anything mission-critical.
-
SaTML Videos Released: Gebru on AGI Ethics and Eugenics
By
–
s from SaTML are now online (
https://
satml.org/videos/)! Few highlights in this short thread. @timnitGebru's keynote on "Eugenics and the Promise of Utopia through Artificial General Intelligence" sparked a lot of discussion already, check it out: https://
youtube.com/watch?v=P7XT4T
WLzJw
… 1/4 -
Jacob Steinhardt on Aligning ML Systems with Human Intent
By
–
Jacob Steinhardt (
@JacobSteinhardt
) with a tutorial on "Aligning ML Systems with Human Intent." "AI alignment" is thrown around a lot, so I enjoyed seeing Jacob cut through the hype and highlight some real technical problems. I was rapt the whole time! https://
youtube.com/watch?v=uPH1xI
iGZ4o
… 3/4 -
SaTML Keynote: Eugenics and AGI Utopia Promise
By
–
s from SaTML are now online (
https://
satml.org/videos/)! Few highlights in this short thread. @timnitGebru
's keynote on "Eugenics and the Promise of Utopia through Artificial General Intelligence" sparked a lot of discussion already, check it out: https://
youtube.com/watch?v=P7XT4T
WLzJw
… 1/4