Make sure to check out the inverse scaling prize, which is a great community effort! Looking forward to evaluating on the Round 2 winners 🙂
RESEARCH
-
U-shaped Scaling and the Limitations of Inverse Scaling Tasks
By
–
Implications: 1. U-shaped scaling means that inverse scaling may not hold when extrapolated to larger models. 2. The term “inverse scaling task” is underspecified. A task can be inverse scaling for one type of prompting and positive or U-shaped for another type of prompting.
-
CoT Prompting Defends Against Inverse Scaling in Math Tasks
By
–
Second, we show that CoT prompting can defend against inverse scaling. For instance, CoT prompting achieves 100% on 7 out of 8 subtasks for Redefine Math.
-
U-shaped Scaling Behavior Emerges at Higher Computational Budgets
By
–
Our results first confirm inverse scaling behavior seen on prior models trained up to 500 zettaFLOPs. But at 2K zettaFLOPs, it becomes U-shaped. U-scaling has also been shown in prior work, such as BIG-Bench.
-
Inverse Scaling Becomes U-Shaped with Larger Language Models
By
–
New preprint!
— Jason Wei (@_jasonwei) 4 novembre 2022
By evaluating 5x larger language models, inverse scaling can become “U-shaped scaling”, which means that performance increases sharply after decreasing.
https://t.co/bZQndKqlB6
These two tasks here are Third Prize winners from the Inverse Scaling Prize. pic.twitter.com/8d3pu8DDrkNew preprint! By evaluating 5x larger language models, inverse scaling can become “U-shaped scaling”, which means that performance increases sharply after decreasing. https://
arxiv.org/abs/2211.02011 These two tasks here are Third Prize winners from the Inverse Scaling Prize. -
JMLR Review Delays: How TMLR Improves Academic Publishing
By
–
I had the same experience with JMLR back in 2015. After 6 months, they hadn't found reviewers. Withdrew the paper and submitted to a different journal. I like that @TmlrOrg doesn't run into this type of friction, since reviewers are expected to review it after being assigned.
-
Democracy increases moral universalism globally survey finds
By
–
Giant worldwide survey looks at universalism (a willingness to treat strangers the same way you treat friends/community members) & finds 26% of people are strongly universalist & 18% are the opposite. Exposure to democracy causally increases universalism. https://
cepr.org/voxeu/columns/
moral-universalism-global-evidence
… -
Meta AI Creates Largest Protein Language Model with 15B Parameters
By
–
Meta AI researchers trained a language model to fill in protein sequence gaps across millions of diverse proteins & scaled up to 15B parameters, creating the largest language model of proteins to date. More on our latest breakthrough in protein folding https://
bit.ly/3WoWcK2 -
ERNIE-Layout Achieves SOTA Results on Document Understanding Tasks
By
–
Introducing ERNIE-Layout, a layout knowledge enhanced document pre-training model that obtained SOTA results on 11 datasets and won 1st place on DocVQA (exceeding 90 for the 1st time) and WebSRC. Check Zero-shot Demo @huggingface
: http://
huggingface.co/spaces/PaddleP
addle/ERNIE-Layout
… -
Research Papers on Click-through Behavior and Search Engine Data
By
–
Paper on click throughs https://
arxiv.org/abs/2102.07385 Paper on Wikipedia being used by search https://
nickmvincent.com/static/wikiser
p_cscw.pdf
…