Training LLMs to Discover Abstractions for Solving Reasoning - Rob and Cosmin
Details
# Training LLMs to Discover Abstractions for Solving Reasoning Problems
This Tuesday we're reviewing "Training LLMs to Discover Abstractions for Solving Reasoning Problems", a new paper from Stanford and CMU sharing insights into using abstractions in reasoning RL
Preparation:
There will not be a prepared presentation but more of a structured conversation.
Spend some time ahead of the meeting skimming the paper so we can have a productive conversation.
Resources:
Paper: https://cohenqu.github.io/rlad.github.io/
Artificial Intelligence
Deep Learning
Machine Intelligence
Machine Learning
Neural Networks