原书出处
Build a Reasoning Model (From Scratch)
Scoring does not always improve the results. Whether and which scorer to use in self-refinement depends on the LLM and needs to be figured out via experimentation on a benchmark dataset like MATH-500.
原书定位详情
来源:a19c7933-4eda-4176-aebd-30fe7e1ad292
正文位置:extracted/Build a Reasoning Model (From Scratch)/_epub-src/OEBPS/Text/chapter-5.html
EPUB SHA-256:52d4d07986020be70f5aac21762dfcf60fcba08db0ba29d4f63957caf12aa377