LLM reasoning
4 stories tagged “LLM reasoning”.
-
A Reinforcement Learning Perspective on OPD: Least-Squares Policy Distillation for Sample-Efficient LLM Reasoning
LSPD recasts on-policy distillation as KL-regularized RL, using least-squares matching and replay to improve s…
-
Unexpected Success, Persistent Failure: Entropy-Driven Credit Assignment for Exploration in LLM Reasoning
EAPO uses entropy to assign token credit in LLM reasoning, penalizing confident failures, rewarding uncertain …
-
Core Principles of Large Language Models
This overview maps LLM foundations: pre-training, prompting, alignment, inference, and reasoning, giving learn…
-
Beware: LLMs Do Not Reason
AlphaGo used search, not intuition; LLM chain-of-thought remains next-token prediction, lacking auditable reas…