#91 - HATTIE ZHOU - Teaching Algorithmic Reasoning via In-context Learning #NeurIPS
About this episode
Support us! https://www.patreon.com/mlst
Hattie Zhou, a PhD student at Université de Montréal and Mila, has set out to understand and explain the performance of modern neural networks, believing it a key factor in building better, more trusted models. Having previously worked as a data scientist at Uber, a private equity analyst at Radar Capital, and an economic consultant at Cornerstone Research, she has recently released a paper in collaboration with the Google Brain team, titled ‘Teaching Algorithmic Reasoning via In-context Learning’. In this work, Hattie identifies and examines four key stages for successfully teaching algorithmic reasoning to large language models (LLMs): formulating algorithms as skills, teaching multiple skills simultaneously, teaching how to combine skills, and teaching how to use skills as tools. Through the application of algorithmic prompting, Hattie has achieved remarkable results, with an order of magnitude error reduction on some tasks compared to the best available baselines. This breakthrough demonstrates algorithmic prompting’s viability as an approach for teaching algorithmic reasoning to LLMs, and may have implications for other tasks requiring similar reasoning capabilities.
TOC
[00:00:00] Hattie Zhou
[00:19:49] Markus Rabe [Google Brain]
Hattie's Twitter - https://twitter.com/oh_that_hat
Website - http://hattiezhou.com/
Teaching Algorithmic Reasoning via In-context Learning [Hattie Zhou, Azade Nova, Hugo Larochelle, Aaron Courville, Behnam Neyshabur, and Hanie Sedghi]
https://arxiv.org/pdf/2211.09066.pdf
Markus Rabe [Google Brain]:
https://twitter.com/markusnrabe
https://research.google/people/106335/
https://www.linkedin.com/in/markusnrabe
Autoformalization with Large Language Models [Albert Jiang Charles Edgar Staats Christian Szegedy Markus Rabe Mateja Jamnik Wenda Li Yuhuai Tony Wu]
https://research.google/pubs/pub51691/
Discord: https://discord.gg/aNPkGUQtc5
YT: https://youtu.be/80i6D2TJdQ4
Get every episode summarized
Each time Machine Learning Street Talk (MLST) publishes, we email you a written briefing from the transcript — the topics, who appeared, and any specific claims, with the ad reads skipped.
Email me new episodesFree for 3 shows. No card needed.
Hosts & guests
No transcript yet
This episode has not been transcribed. Request it and it moves to the front of the queue.
More episodes
More from Machine Learning Street Talk (MLST)
AI 2040: Plan A report - Daniel Kokotajlo & Thomas Larsen
Machine Learning Street Talk (MLST)
Designing How AI Grows — Tom McGrath
Machine Learning Street Talk (MLST)
Stealing Reasoning Traces from Proprietary LLM APIs — Ilia Shumailov & Alexander...
Machine Learning Street Talk (MLST)
Every Exponential Ends — Silicon Valley Forgot — Adam Becker
Machine Learning Street Talk (MLST)