rasbt's 'Reasoning from Scratch' ep.5 covers log-prob scoring and self-refinement
pandeyparul · x · 2026-09-26
Sebastian Raschka's "Reasoning from scratch" series reaches round 5, covering log-probability scoring for comparing and ranking model answers (also foundational for cross-entropy loss in pre-training and distillation) and self-refinement. The chapter walks through inference-time scaling recap, loading a pretrained LLM, and building a rule-based scorer, with full timestamps.
More from Research
- Anthropic: Claude computes nine-loop scattering amplitudes, breaking the eight-loop record — LucaAmb · 2026-09-26
- Microsoft open-sources Fabric-RLM: LLMs write code to recursively chew through big data — adnan_hashmi · 2026-09-26
- New paper asks where to draw the line on mental privacy as BCI decoding improves — melnykowycz · 2026-09-26
- Where to get the 277-page Foundations of LLMs PDF and what chapter 5 covers — mdancho84 · 2026-09-26
- LLM textbook thread: decoding algorithms, acceleration, and inference-time scaling in chapter 5 — mdancho84 · 2026-09-26
- Free 277-page LLM textbook Foundations of Large Language Models updated with a new chapter — mdancho84 · 2026-09-26