Class Central is learner-supported. When you buy through links on our site, we may earn an affiliate commission.

YouTube

Improving LLM Accuracy with Monte Carlo Tree Search

Trelis Research via YouTube

Overview

Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only!
Explore a 33-minute video lecture on enhancing Large Language Model (LLM) accuracy using Monte Carlo Tree Search. Dive into the process of boosting Llama 3 8B performance to rival GPT-4 on specific benchmarks. Understand the impact of prompting on accuracy and learn the mechanics of Monte Carlo tree search, including the balance between exploitation and exploration. Follow along with Jupyter Notebook code demonstrations, witness Monte Carlo Tree Search applied to a simple example, and discover its potential for improving performance on mathematical problems. Examine the limitations of Monte Carlo performance boosts and access additional resources for further study.

Syllabus

Large Language Models Make Things Up!
Boosting Llama 3 8B performance to GPT-4 only on certain benchmarks!
How prompting affects accuracy
How Monte Carlo tree search works
Balancing exploitation with exploration
Jupyter Notebook Code
Testing Monte Carlo Tree Search on a simple example
Boosting Performance on Maths problems
Limitations on Monte Carlo Performance Boosts
Resources

Taught by

Trelis Research

Reviews

Start your review of Improving LLM Accuracy with Monte Carlo Tree Search

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.