Improving LLM accuracy with Monte Carlo Tree Search

➡️ Get Life-time Access to the ADVANCED-inference Repo (incl. notebooks in this vid.): https://trelis.com/enterprise-server-... ➡️ Trelis Newsletter: https://blog.Trelis.com ➡️ Trelis Resources and Support: https://Trelis.com/About VIDEO RESOURCES: Slides: https://docs.google.com/presentation/... Paper: https://arxiv.org/abs/2406.07394 (Accessing GPT-4 level Mathematical Olympiad Solutions via Monte Carlo Tree Self-refine with LLaMa-3 8B) Code from Paper: https://github.com/trotsky1997/MathBl... TIMESTAMPS: 0:00 Large Language Models Make Things Up! 0:42 Boosting Llama 3 8B performance to GPT-4 (only on certain benchmarks!) 3:13 How prompting affects accuracy 4:58 How Monte Carlo tree search works 7:49 Balancing exploitation with exploration 10:18 Jupyter Notebook Code 26:59 Testing Monte Carlo Tree Search on a simple example 29:16 Boosting Performance on Maths problems 31:48 Limitations on Monte Carlo Performance Boosts 32:58 Resources