Advanced Reasoning with Large Language Models with Chain of Thought Prompting | Paper explained!

Paper link: arxiv.org/abs/2201.11903
Abstract: We explore how generating a chain of thought -- a series of intermediate reasoning steps -- significantly improves the ability of large language models to perform complex reasoning. In particular, we show how such reasoning abilities emerge naturally in sufficiently large language models via a simple method called chain of thought prompting, where a few chain of thought demonstrations are provided as exemplars in prompting. Experiments on three large language models show that chain of thought prompting improves performance on a range of arithmetic, commonsense, and symbolic reasoning tasks. The empirical gains can be striking. For instance, prompting a 540B-parameter language model with just eight chain of thought exemplars achieves state of the art accuracy on the GSM8K benchmark of math word problems, surpassing even finetuned GPT-3 with a verifier.
#artificialintelligence #nlproc #nlp #deeplearning #ml

[@andybaker4861]

She's a robot, right? She's good. It was her occasionally unnatural inflection that tipped me off.

[@TheGlobalNLPLab]

Yes indeed! I'm using www.synthesia.io/

[@tNotimportant]

It wasn't the inflections that got me it was the unnatural movements.

[@ChaoticNeutralMatt]

That uncanny valley consistency. So weird.

[@hailking5588]

Great videos! I have question regarding the data, did they actually added the chain of thoughts to all of the training data, or only some of them?

[@WillGilpin]

UA-cam will add subtitles if we need them. No need to add them to the videos - they are distracting

[@temanapotaka-dewes9097]

CoT prompting seems to be a logical solution to getting the LLM to do what you want it to do.
What are the limitations of CoT prompting?

[@TheGlobalNLPLab]

Thanks for the comment! The limitations might be that for some tasks CoT might potentially be overcomplicating / diluting the target problem. Also, CoT increases the input/output sequence lengths, leading to slower inference / greater cost. But it's definitely a great technique to test for your problem!

[@best_songs_ever3889]

is the host also computer generated using AI...!!🤔

[@morris5648]

What no human?

[@incameet]

B should be read as Billion not as B.

[@TheGlobalNLPLab]

Thanks for the comment! Yeah, that's because the video is actually created with AI! Check out: www.synthesia.io/?via=nlplab

[@firelordzaki1600]

Bra go read that actual paper it's only 43pgs. Whoops I meant pages! 😬

[@lemark221]

nothing new, She didnt even bother to run a test herself lol waste of time.