Posts tagged: llm-reasoning
-
Optimizing LLM reasoning is not just about training bigger models
How inference-time scaling, self-consistency, verifiers, and reasoning budgets improve LLM quality, and when not to use them due to high costs.
→ -
OnePiece at Shopee: How LLM-style reasoning enters a ranking system
Notes on the OnePiece paper and how context engineering and reasoning are introduced into an industrial cascade ranking system.
→