Uploaded September 2026 | Updated November 2026, 4 hours ago
This second video on inference-time scaling, introduces different scoring functions to break ties in majority voting and also introduces self-refinement.
- Reasoning playlist: youtube.com/watch?v=Kh9mqTzjuEQ&list=PLfrHAQCRxtUs
- Reasoning Book: amzn.to/4aAKiFY
- Reasoning GitHub repo: github.com/rasbt/reasoning-from-scratch
- LLMs from Scratch book: amzn.to/4fqvn0D
- LLMs from Scratch repo: github.com/rasbt/LLMs-from-scratch
- LLMs from Scratch playlist: youtube.com/watch?v=yAcWnfsZhzo&list=PLTKMiZHVd_2IIEsoJrWACkIxLRdfMlw11&index=1
00:00 Introduction and inference-time scaling recap
05:02 Loading the pretrained LLM
08:00 Comparing and scoring model answers
10:18 Building a rule-based scorer
17:53 Token probabilities and sequence likelihood
26:47 Computing token probabilities in PyTorch
30:12 Token indexing and shifted targets
37:27 Log probabilities and numerical stability
45:57 Scoring answers with average log probabilities
56:24 How self-refinement works
59:07 Generating critiques and revised answers
1:01:00 Implementing the self-refinement loop
1:05:57 MATH-500 evaluation results
1:07:35 Takeaways and next steps
This second video on inference-time scaling, introduces different scoring functions to break ties in majority voting and also introduces self-refinement.
- Reasoning playlist: youtube.com/watch?v=Kh9mqTzjuEQ&list=PLfrHAQCRxtUs
- Reasoning Book: amzn.to/4aAKiFY
- Reasoning GitHub repo: github.com/rasbt/reasoning-from-scratch
- LLMs from Scratch book: amzn.to/4fqvn0D
- LLMs from Scratch repo: github.com/rasbt/LLMs-from-scratch
- LLMs from Scratch playlist: youtube.com/watch?v=yAcWnfsZhzo&list=PLTKMiZHVd_2IIEsoJrWACkIxLRdfMlw11&index=1
00:00 Introduction and inference-time scaling recap
05:02 Loading the pretrained LLM
08:00 Comparing and scoring model answers
10:18 Building a rule-based scorer
17:53 Token probabilities and sequence likelihood
26:47 Computing token probabilities in PyTorch
30:12 Token indexing and shifted targets
37:27 Log probabilities and numerical stability
45:57 Scoring answers with average log probabilities
56:24 How self-refinement works
59:07 Generating critiques and revised answers
1:01:00 Implementing the self-refinement loop
1:05:57 MATH-500 evaluation results
1:07:35 Takeaways and next steps










